Understanding the inner workings of Transformers is crucial for achieving more accurate and efficient predictions. In this work, we analyze the computation performed by Transformers in the layers after the top-1 prediction has become fixed, which has been previously referred to as the "saturation event". We expand the concept of saturation events for top-k tokens, demonstrating that similar saturation events occur across language, vision, and speech models. We find that these saturation events happen in order of the corresponding tokens' ranking, i.e., the model first decides on the top ranking token, then the second highest ranking token, and so on. This phenomenon seems intrinsic to the Transformer architecture, occurring across different architectural variants (decoder-only, encoder-only, and to a lesser extent full-Transformer), and even in untrained Transformers. We propose an underlying mechanism of task transition for this sequential saturation, where task k corresponds to predicting the k-th most probable token, and the saturation events are in fact discrete transitions between the tasks. In support of this we show that it is possible to predict the current task from hidden layer embedding. Furthermore, using an intervention method we demonstrate that we can cause the model to switch from one task to the next. Finally, leveraging our findings, we introduce a novel token-level early-exit strategy, which surpasses existing methods in balancing performance and efficiency.

本研究探讨了变换器中顶级标记预测固定后的计算过程，填补了对“饱和事件”的理解空白。我们提出了任务转移的机制，该机制解释了这些饱和事件的顺序发生，并为引入一种新的标记级早期退出策略奠定了基础，显著提升了性能与效率的平衡。

超越前1的视角：变换器按顺序确定顶级标记