Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5295 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.6874. Min Range: -3.6874
Max Act: 3.6874. Min Act: -0.0001
Data Index: 1557712 (Python Code)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6874. Min Range: -3.6874
Max Act: 3.5885. Min Act: -0.0001
Data Index: 1074849 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6874. Min Range: -3.6874
Max Act: 3.2186. Min Act: -0.0001
Data Index: 997319 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6874. Min Range: -3.6874
Max Act: 3.3228. Min Act: -0.0001
Data Index: 1587186 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6874. Min Range: -3.6874
Max Act: 3.2685. Min Act: -0.0001
Data Index: 549882 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6874. Min Range: -3.6874
Max Act: 3.0050. Min Act: -0.0001
Data Index: 1134950 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.9527. Min Act: -0.0001
Data Index: 762868 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.9767. Min Act: -0.0001
Data Index: 489555 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.8802. Min Act: -0.0001
Data Index: 1231878 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.8139. Min Act: -0.0001
Data Index: 926947 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.8303. Min Act: -0.0001
Data Index: 434414 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.6775. Min Act: -0.0001
Data Index: 792774 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.8920. Min Act: -0.0001
Data Index: 1083942 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.6172. Min Act: -0.0001
Data Index: 88470 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.7344. Min Act: -0.0001
Data Index: 220504 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.6132. Min Act: -0.0001
Data Index: 356457 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.7236. Min Act: -0.0001
Data Index: 73452 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.6875. Min Act: -0.0001
Data Index: 366698 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.6759. Min Act: -0.0001
Data Index: 1234501 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6874. Min Range: -3.6874
Max Act: 2.6731. Min Act: -0.0001
Data Index: 848809 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19