Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1252 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.4864. Min Act: -0.0001
Data Index: 1456601 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.4508. Min Act: -0.0001
Data Index: 457308 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.4311. Min Act: -0.0001
Data Index: 1693749 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3831. Min Act: -0.0001
Data Index: 816290 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.4152. Min Act: -0.0001
Data Index: 962469 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.4076. Min Act: -0.0001
Data Index: 1621151 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3912. Min Act: -0.0001
Data Index: 202440 (The Pile)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3956. Min Act: -0.0001
Data Index: 1857485 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3647. Min Act: -0.0001
Data Index: 347593 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3882. Min Act: -0.0001
Data Index: 404642 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3874. Min Act: -0.0001
Data Index: 51390 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3535. Min Act: -0.0001
Data Index: 1590547 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.4025. Min Act: -0.0001
Data Index: 1429975 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3853. Min Act: -0.0001
Data Index: 1855230 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.4081. Min Act: -0.0001
Data Index: 1039559 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3693. Min Act: -0.0001
Data Index: 572040 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3645. Min Act: -0.0001
Data Index: 1632218 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3625. Min Act: -0.0001
Data Index: 876240 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3744. Min Act: -0.0001
Data Index: 451213 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4864. Min Range: -0.4864
Max Act: 0.3698. Min Act: -0.0001
Data Index: 413695 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19