Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2659 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.3007. Min Range: -2.3007
Max Act: 2.3007. Min Act: -0.0000
Data Index: 348569 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.7313. Min Act: -0.0000
Data Index: 1138142 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.8642. Min Act: -0.0000
Data Index: 394235 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.6148. Min Act: -0.0000
Data Index: 1848121 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.6632. Min Act: -0.0000
Data Index: 1767663 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.7269. Min Act: -0.0000
Data Index: 779927 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.5552. Min Act: -0.0000
Data Index: 1754468 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.6334. Min Act: -0.0000
Data Index: 1553056 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.4855. Min Act: -0.0000
Data Index: 592417 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.4753. Min Act: -0.0000
Data Index: 1758678 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.4603. Min Act: -0.0000
Data Index: 1100493 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.6143. Min Act: -0.0000
Data Index: 1996140 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.4327. Min Act: -0.0000
Data Index: 329048 (The Pile)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.4423. Min Act: -0.0000
Data Index: 205270 (The Pile)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.5961. Min Act: -0.0000
Data Index: 449100 (The Pile)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.4124. Min Act: -0.0000
Data Index: 481304 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.5912. Min Act: -0.0000
Data Index: 1155512 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.4853. Min Act: -0.0000
Data Index: 599823 (The Pile)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.5825. Min Act: -0.0000
Data Index: 1536580 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3007. Min Range: -2.3007
Max Act: 1.4947. Min Act: -0.0000
Data Index: 335481 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19