Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2888 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.7348. Min Act: -0.0000
Data Index: 1857516 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.3845. Min Act: -0.0000
Data Index: 1646114 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.3176. Min Act: -0.0000
Data Index: 992580 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.1535. Min Act: -0.0000
Data Index: 1226688 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.2573. Min Act: -0.0000
Data Index: 596155 (The Pile)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.2548. Min Act: -0.0000
Data Index: 1208648 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.1307. Min Act: -0.0000
Data Index: 1685872 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.1503. Min Act: -0.0000
Data Index: 1407107 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.1017. Min Act: -0.0000
Data Index: 281685 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.0758. Min Act: -0.0000
Data Index: 939254 (The Pile)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7348. Min Range: -2.7348
Max Act: 1.9541. Min Act: -0.0000
Data Index: 1191236 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7348. Min Range: -2.7348
Max Act: 1.9322. Min Act: -0.0000
Data Index: 741240 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.0516. Min Act: -0.0000
Data Index: 176405 (The Pile)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7348. Min Range: -2.7348
Max Act: 1.9152. Min Act: -0.0000
Data Index: 841437 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.0120. Min Act: -0.0000
Data Index: 1405877 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7348. Min Range: -2.7348
Max Act: 2.0956. Min Act: -0.0000
Data Index: 297935 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7348. Min Range: -2.7348
Max Act: 1.9202. Min Act: -0.0000
Data Index: 600491 (The Pile)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7348. Min Range: -2.7348
Max Act: 1.9097. Min Act: -0.0000
Data Index: 1520785 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7348. Min Range: -2.7348
Max Act: 1.9071. Min Act: -0.0000
Data Index: 937001 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7348. Min Range: -2.7348
Max Act: 1.9103. Min Act: -0.0000
Data Index: 1291428 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19