Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3425 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.9984. Min Act: -0.0001
Data Index: 1026297 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.5002. Min Act: -0.0001
Data Index: 570537 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.6631. Min Act: -0.0001
Data Index: 574484 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.6430. Min Act: -0.0001
Data Index: 1009348 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.6141. Min Act: -0.0001
Data Index: 454536 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.5180. Min Act: -0.0001
Data Index: 303076 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.5799. Min Act: -0.0001
Data Index: 1278770 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.6719. Min Act: -0.0001
Data Index: 62336 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.5009. Min Act: -0.0001
Data Index: 352479 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.1144. Min Act: -0.0001
Data Index: 496725 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.3221. Min Act: -0.0001
Data Index: 358507 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.5734. Min Act: -0.0001
Data Index: 1157091 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.4504. Min Act: -0.0001
Data Index: 230050 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.4924. Min Act: -0.0001
Data Index: 915952 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.4533. Min Act: -0.0001
Data Index: 82834 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.4719. Min Act: -0.0001
Data Index: 912791 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.4311. Min Act: -0.0001
Data Index: 436742 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.3718. Min Act: -0.0001
Data Index: 84662 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.2177. Min Act: -0.0001
Data Index: 390073 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9984. Min Range: -2.9984
Max Act: 2.3286. Min Act: -0.0001
Data Index: 1114084 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19