Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 59 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.6624. Min Act: -0.0000
Data Index: 670705 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.4345. Min Act: -0.0000
Data Index: 955936 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.4281. Min Act: -0.0000
Data Index: 733753 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.3546. Min Act: -0.0000
Data Index: 611479 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.4757. Min Act: -0.0000
Data Index: 168024 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.3535. Min Act: -0.0000
Data Index: 243683 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.1988. Min Act: -0.0001
Data Index: 1143829 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.3072. Min Act: -0.0000
Data Index: 614365 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.2959. Min Act: -0.0000
Data Index: 1120901 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.2801. Min Act: -0.0000
Data Index: 610358 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.2475. Min Act: -0.0000
Data Index: 136462 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.2485. Min Act: -0.0000
Data Index: 52991 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.2765. Min Act: -0.0001
Data Index: 92548 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.1193. Min Act: -0.0000
Data Index: 48012 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.0202. Min Act: -0.0000
Data Index: 1080698 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.0144. Min Act: -0.0001
Data Index: 315033 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.0828. Min Act: -0.0000
Data Index: 561572 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.0200. Min Act: -0.0001
Data Index: 97794 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6624. Min Range: -1.6624
Max Act: 1.0206. Min Act: -0.0001
Data Index: 654807 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6624. Min Range: -1.6624
Max Act: 0.9520. Min Act: -0.0001
Data Index: 50648 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19