Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3032 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.5850. Min Act: -0.0001
Data Index: 982039 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.4122. Min Act: -0.0001
Data Index: 862956 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.3220. Min Act: -0.0001
Data Index: 780142 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.2557. Min Act: -0.0000
Data Index: 908925 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.1219. Min Act: -0.0001
Data Index: 788778 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.1153. Min Act: -0.0001
Data Index: 900911 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.2252. Min Act: -0.0001
Data Index: 16475 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.1162. Min Act: -0.0001
Data Index: 607180 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.0895. Min Act: -0.0000
Data Index: 910466 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.1808. Min Act: -0.0001
Data Index: 759861 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.0711. Min Act: -0.0001
Data Index: 180696 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.2781. Min Act: -0.0001
Data Index: 55114 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.1580. Min Act: -0.0001
Data Index: 993989 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.0513. Min Act: -0.0000
Data Index: 1403508 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.0282. Min Act: -0.0000
Data Index: 1092772 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.0282. Min Act: -0.0000
Data Index: 1379469 (Python Code)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.1174. Min Act: -0.0001
Data Index: 1036234 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.1036. Min Act: -0.0000
Data Index: 955109 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.2145. Min Act: -0.0001
Data Index: 1008083 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5850. Min Range: -2.5850
Max Act: 2.0913. Min Act: -0.0001
Data Index: 591555 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19