Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 69 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.1975. Min Range: -3.1975
Max Act: 3.1975. Min Act: -0.0001
Data Index: 540242 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.7513. Min Act: -0.0001
Data Index: 1132426 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.5963. Min Act: -0.0001
Data Index: 1094936 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.7149. Min Act: -0.0001
Data Index: 1188912 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.6121. Min Act: -0.0001
Data Index: 334741 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.9940. Min Act: -0.0001
Data Index: 658664 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.6831. Min Act: -0.0001
Data Index: 1261246 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.4488. Min Act: -0.0001
Data Index: 767523 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.3049. Min Act: -0.0001
Data Index: 283419 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.4087. Min Act: -0.0001
Data Index: 864376 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.1417. Min Act: -0.0001
Data Index: 789171 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.3790. Min Act: -0.0001
Data Index: 1302389 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.1056. Min Act: -0.0001
Data Index: 12579 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.1588. Min Act: -0.0001
Data Index: 1068683 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.1480. Min Act: -0.0001
Data Index: 540727 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.2503. Min Act: -0.0001
Data Index: 1111632 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.0052. Min Act: -0.0001
Data Index: 992133 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.1890. Min Act: -0.0001
Data Index: 235633 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.0274. Min Act: -0.0001
Data Index: 57136 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1975. Min Range: -3.1975
Max Act: 2.0751. Min Act: -0.0001
Data Index: 695975 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19