Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1032 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.8485. Min Act: -0.0001
Data Index: 88953 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7796. Min Act: -0.0001
Data Index: 538775 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7816. Min Act: -0.0001
Data Index: 1112767 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7873. Min Act: -0.0001
Data Index: 890754 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7092. Min Act: -0.0001
Data Index: 244762 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.6901. Min Act: -0.0001
Data Index: 117349 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7108. Min Act: -0.0001
Data Index: 638199 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7089. Min Act: -0.0001
Data Index: 1308324 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7307. Min Act: -0.0001
Data Index: 1597074 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.6869. Min Act: -0.0001
Data Index: 623963 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7098. Min Act: -0.0001
Data Index: 255429 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7062. Min Act: -0.0001
Data Index: 1326296 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7234. Min Act: -0.0001
Data Index: 273436 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.6975. Min Act: -0.0001
Data Index: 353642 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7099. Min Act: -0.0001
Data Index: 1449384 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.6673. Min Act: -0.0001
Data Index: 868563 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.6565. Min Act: -0.0001
Data Index: 832585 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.7073. Min Act: -0.0001
Data Index: 605631 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.6789. Min Act: -0.0001
Data Index: 647361 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8485. Min Range: -0.8485
Max Act: 0.6753. Min Act: -0.0001
Data Index: 137156 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19