Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 340 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.2674. Min Range: -4.2674
Max Act: 4.2674. Min Act: -0.0001
Data Index: 235521 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.7898. Min Act: -0.0001
Data Index: 168000 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.9566. Min Act: -0.0001
Data Index: 1304901 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.5540. Min Act: -0.0001
Data Index: 377976 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.7544. Min Act: -0.0001
Data Index: 942972 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.6243. Min Act: -0.0001
Data Index: 1287463 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.4566. Min Act: -0.0001
Data Index: 787989 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.2601. Min Act: -0.0001
Data Index: 692965 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.1066. Min Act: -0.0001
Data Index: 282227 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.1555. Min Act: -0.0001
Data Index: 65892 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.0971. Min Act: -0.0001
Data Index: 538072 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.0992. Min Act: -0.0001
Data Index: 1063537 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2674. Min Range: -4.2674
Max Act: 1.9689. Min Act: -0.0001
Data Index: 528866 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.1752. Min Act: -0.0001
Data Index: 28986 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2674. Min Range: -4.2674
Max Act: 2.0527. Min Act: -0.0001
Data Index: 1248041 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2674. Min Range: -4.2674
Max Act: 1.9317. Min Act: -0.0001
Data Index: 999141 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2674. Min Range: -4.2674
Max Act: 1.9195. Min Act: -0.0001
Data Index: 113249 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2674. Min Range: -4.2674
Max Act: 1.7855. Min Act: -0.0001
Data Index: 810916 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2674. Min Range: -4.2674
Max Act: 1.8052. Min Act: -0.0001
Data Index: 1346649 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2674. Min Range: -4.2674
Max Act: 1.9815. Min Act: -0.0001
Data Index: 57568 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19