Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 54 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.1142. Min Act: -0.0002
Data Index: 1093741 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0669. Min Act: -0.0002
Data Index: 1550814 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0627. Min Act: -0.0002
Data Index: 1545138 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0606. Min Act: -0.0002
Data Index: 1215218 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0535. Min Act: -0.0002
Data Index: 495313 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0526. Min Act: -0.0002
Data Index: 78209 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0456. Min Act: -0.0002
Data Index: 413260 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0470. Min Act: -0.0002
Data Index: 716738 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0451. Min Act: -0.0002
Data Index: 1847246 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0448. Min Act: -0.0002
Data Index: 4179 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0435. Min Act: -0.0002
Data Index: 65657 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0419. Min Act: -0.0002
Data Index: 1516467 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0426. Min Act: -0.0002
Data Index: 780397 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0408. Min Act: -0.0002
Data Index: 627979 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0395. Min Act: -0.0002
Data Index: 56595 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0393. Min Act: -0.0002
Data Index: 460796 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0376. Min Act: -0.0002
Data Index: 1144121 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0357. Min Act: -0.0002
Data Index: 478340 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0366. Min Act: -0.0002
Data Index: 1322635 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1142. Min Range: -0.1142
Max Act: 0.0357. Min Act: -0.0002
Data Index: 848365 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19