Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1572 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.2978. Min Range: -3.2978
Max Act: 3.2978. Min Act: -0.0001
Data Index: 469627 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.8393. Min Act: -0.0001
Data Index: 425863 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.7709. Min Act: -0.0001
Data Index: 265580 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.4933. Min Act: -0.0001
Data Index: 988974 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.3415. Min Act: -0.0001
Data Index: 223113 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.3966. Min Act: -0.0001
Data Index: 94510 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.3405. Min Act: -0.0001
Data Index: 866862 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.6820. Min Act: -0.0001
Data Index: 1321794 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.3955. Min Act: -0.0000
Data Index: 596474 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.3697. Min Act: -0.0001
Data Index: 269513 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2978. Min Range: -3.2978
Max Act: 2.0833. Min Act: -0.0001
Data Index: 1245548 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.8574. Min Act: -0.0001
Data Index: 932743 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.8015. Min Act: -0.0001
Data Index: 541810 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.7977. Min Act: -0.0001
Data Index: 1162283 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.6718. Min Act: -0.0001
Data Index: 1292464 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.6639. Min Act: -0.0001
Data Index: 558015 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.9016. Min Act: -0.0001
Data Index: 803828 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.7547. Min Act: -0.0001
Data Index: 38448 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.7332. Min Act: -0.0001
Data Index: 987842 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2978. Min Range: -3.2978
Max Act: 1.7106. Min Act: -0.0001
Data Index: 1020097 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19