Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3466 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0194. Min Act: -0.0000
Data Index: 676315 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0186. Min Act: -0.0000
Data Index: 942209 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0186. Min Act: 0.0000
Data Index: 1479719 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0179. Min Act: -0.0001
Data Index: 1411354 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0185. Min Act: -0.0000
Data Index: 1448229 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0183. Min Act: -0.0000
Data Index: 559472 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0181. Min Act: -0.0000
Data Index: 424870 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0180. Min Act: -0.0001
Data Index: 360516 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0180. Min Act: -0.0000
Data Index: 1137483 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0180. Min Act: -0.0000
Data Index: 1652835 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0000
Data Index: 225588 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0001
Data Index: 392468 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0000
Data Index: 409812 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0001
Data Index: 428578 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0000
Data Index: 18286 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0001
Data Index: 59274 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0000
Data Index: 53363 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0000
Data Index: 400748 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0000
Data Index: 350997 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0194. Min Range: -0.0194
Max Act: 0.0178. Min Act: -0.0000
Data Index: 370996 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19