Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3407 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.1698. Min Range: -4.1698
Max Act: 4.1698. Min Act: -0.0001
Data Index: 284468 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1698. Min Range: -4.1698
Max Act: 3.2752. Min Act: -0.0001
Data Index: 1006103 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1698. Min Range: -4.1698
Max Act: 3.2733. Min Act: -0.0001
Data Index: 1296549 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1698. Min Range: -4.1698
Max Act: 3.2013. Min Act: -0.0001
Data Index: 920587 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1698. Min Range: -4.1698
Max Act: 3.0506. Min Act: -0.0001
Data Index: 954426 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.9321. Min Act: -0.0001
Data Index: 1211616 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.9177. Min Act: -0.0001
Data Index: 1263409 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.7308. Min Act: -0.0001
Data Index: 692968 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.6887. Min Act: -0.0001
Data Index: 210176 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.9135. Min Act: -0.0001
Data Index: 110443 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.6281. Min Act: -0.0001
Data Index: 289291 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.5348. Min Act: -0.0001
Data Index: 1330982 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.6309. Min Act: -0.0001
Data Index: 422039 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.4143. Min Act: -0.0001
Data Index: 1257880 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.4454. Min Act: -0.0001
Data Index: 507841 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.2007. Min Act: -0.0001
Data Index: 108655 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.5075. Min Act: -0.0001
Data Index: 669977 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.2949. Min Act: -0.0001
Data Index: 950017 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.3325. Min Act: -0.0001
Data Index: 20814 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1698. Min Range: -4.1698
Max Act: 2.1657. Min Act: -0.0001
Data Index: 708502 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19