Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2775 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.8785. Min Act: -0.0001
Data Index: 1058104 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.6938. Min Act: -0.0000
Data Index: 530701 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.7249. Min Act: -0.0001
Data Index: 992342 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.3852. Min Act: -0.0001
Data Index: 650829 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.5056. Min Act: -0.0001
Data Index: 1260765 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.4523. Min Act: -0.0001
Data Index: 1242200 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.4238. Min Act: -0.0001
Data Index: 382994 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.3158. Min Act: -0.0001
Data Index: 93297 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.1756. Min Act: -0.0001
Data Index: 785132 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8785. Min Range: -4.8785
Max Act: 3.9910. Min Act: -0.0001
Data Index: 862049 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.3022. Min Act: -0.0001
Data Index: 794209 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8785. Min Range: -4.8785
Max Act: 3.5040. Min Act: -0.0001
Data Index: 709765 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8785. Min Range: -4.8785
Max Act: 3.9189. Min Act: -0.0001
Data Index: 920884 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.0209. Min Act: -0.0001
Data Index: 898735 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8785. Min Range: -4.8785
Max Act: 3.8610. Min Act: -0.0001
Data Index: 415909 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8785. Min Range: -4.8785
Max Act: 3.9894. Min Act: -0.0001
Data Index: 1062445 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.1738. Min Act: -0.0000
Data Index: 1304685 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8785. Min Range: -4.8785
Max Act: 4.0986. Min Act: -0.0001
Data Index: 879124 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8785. Min Range: -4.8785
Max Act: 3.7671. Min Act: -0.0001
Data Index: 231574 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8785. Min Range: -4.8785
Max Act: 3.8974. Min Act: -0.0001
Data Index: 92791 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19