Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2686 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.4362. Min Act: -0.0001
Data Index: 787744 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.2770. Min Act: -0.0001
Data Index: 531054 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.2962. Min Act: -0.0001
Data Index: 164144 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0844. Min Act: -0.0001
Data Index: 1115077 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0116. Min Act: -0.0001
Data Index: 105697 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0969. Min Act: -0.0001
Data Index: 639009 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4362. Min Range: -2.4362
Max Act: 1.8986. Min Act: -0.0001
Data Index: 214220 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.2355. Min Act: -0.0001
Data Index: 1133891 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4362. Min Range: -2.4362
Max Act: 1.9709. Min Act: -0.0001
Data Index: 236492 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0673. Min Act: -0.0001
Data Index: 520533 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0568. Min Act: -0.0001
Data Index: 962756 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0490. Min Act: -0.0001
Data Index: 742804 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0835. Min Act: -0.0001
Data Index: 865175 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0221. Min Act: -0.0001
Data Index: 855628 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4362. Min Range: -2.4362
Max Act: 1.9083. Min Act: -0.0001
Data Index: 633883 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4362. Min Range: -2.4362
Max Act: 1.9289. Min Act: -0.0001
Data Index: 1078277 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4362. Min Range: -2.4362
Max Act: 2.0009. Min Act: -0.0001
Data Index: 1022640 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4362. Min Range: -2.4362
Max Act: 1.9428. Min Act: -0.0001
Data Index: 1266363 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4362. Min Range: -2.4362
Max Act: 1.8945. Min Act: -0.0001
Data Index: 1253870 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4362. Min Range: -2.4362
Max Act: 1.9617. Min Act: -0.0001
Data Index: 144171 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19