Model: SoLU Model: 2 Layers, 2944 Neurons per Layer
Dataset: The Pile
Neuron 2086 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l-pile')
Text #0
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.3284. Min Act: -0.0002
Data Index: 675969 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2883. Min Act: -0.0002
Data Index: 794784 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2720. Min Act: -0.0002
Data Index: 89660 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2552. Min Act: -0.0002
Data Index: 325168 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2359. Min Act: -0.0002
Data Index: 557080 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2364. Min Act: -0.0002
Data Index: 1018945 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2190. Min Act: -0.0002
Data Index: 117434 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2239. Min Act: -0.0002
Data Index: 341693 (The Pile)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2191. Min Act: -0.0002
Data Index: 973962 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2145. Min Act: -0.0002
Data Index: 1205291 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2221. Min Act: -0.0002
Data Index: 1565768 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2224. Min Act: -0.0002
Data Index: 1313747 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2113. Min Act: -0.0002
Data Index: 429631 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2193. Min Act: -0.0002
Data Index: 695720 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2073. Min Act: -0.0002
Data Index: 846043 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2099. Min Act: -0.0002
Data Index: 1861033 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2031. Min Act: -0.0002
Data Index: 447713 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.2001. Min Act: -0.0002
Data Index: 998103 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.1947. Min Act: -0.0002
Data Index: 596534 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3284. Min Range: -0.3284
Max Act: 0.1976. Min Act: -0.0002
Data Index: 86778 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19