Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1198 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.7103. Min Act: -0.0003
Data Index: 295715 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.6228. Min Act: -0.0003
Data Index: 1508543 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.6158. Min Act: -0.0003
Data Index: 352551 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5454. Min Act: -0.0003
Data Index: 42254 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5532. Min Act: -0.0003
Data Index: 1105114 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5297. Min Act: -0.0003
Data Index: 1295619 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5302. Min Act: -0.0003
Data Index: 1681659 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5473. Min Act: -0.0003
Data Index: 120416 (The Pile)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5371. Min Act: -0.0003
Data Index: 535091 (The Pile)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5165. Min Act: -0.0003
Data Index: 1468468 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5295. Min Act: -0.0003
Data Index: 588440 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5284. Min Act: -0.0003
Data Index: 1024451 (The Pile)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5109. Min Act: -0.0003
Data Index: 652916 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5254. Min Act: -0.0003
Data Index: 1850292 (The Pile)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5016. Min Act: -0.0003
Data Index: 1380727 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5165. Min Act: -0.0003
Data Index: 1742813 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5347. Min Act: -0.0003
Data Index: 281139 (The Pile)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5129. Min Act: -0.0003
Data Index: 709714 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.4958. Min Act: -0.0003
Data Index: 1930007 (The Pile)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7103. Min Range: -0.7103
Max Act: 0.5143. Min Act: -0.0003
Data Index: 696990 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19