Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3047 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.7346. Min Act: -0.0001
Data Index: 566497 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.8008. Min Act: -0.0001
Data Index: 305072 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.7325. Min Act: -0.0001
Data Index: 881024 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.8025. Min Act: -0.0001
Data Index: 75653 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.7406. Min Act: -0.0001
Data Index: 450865 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.6893. Min Act: -0.0001
Data Index: 43788 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.6668. Min Act: -0.0001
Data Index: 804581 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.7480. Min Act: -0.0001
Data Index: 759466 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.6590. Min Act: -0.0001
Data Index: 885080 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.5184. Min Act: -0.0001
Data Index: 919033 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.5114. Min Act: -0.0001
Data Index: 260552 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.5855. Min Act: -0.0001
Data Index: 878252 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.5795. Min Act: -0.0001
Data Index: 631162 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.5903. Min Act: -0.0001
Data Index: 1328051 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.6259. Min Act: -0.0001
Data Index: 1150240 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.5405. Min Act: -0.0001
Data Index: 837060 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.6218. Min Act: -0.0001
Data Index: 1327726 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.6927. Min Act: -0.0001
Data Index: 795912 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.5459. Min Act: -0.0001
Data Index: 1234144 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8025. Min Range: -1.8025
Max Act: 1.7204. Min Act: -0.0001
Data Index: 296036 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19