Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3480 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7187. Min Range: -2.7187
Max Act: 2.7187. Min Act: -0.0001
Data Index: 550999 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7187. Min Range: -2.7187
Max Act: 2.2778. Min Act: -0.0001
Data Index: 994062 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7187. Min Range: -2.7187
Max Act: 2.2261. Min Act: -0.0001
Data Index: 1014353 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7187. Min Range: -2.7187
Max Act: 2.1977. Min Act: -0.0001
Data Index: 683240 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7187. Min Range: -2.7187
Max Act: 2.2949. Min Act: -0.0001
Data Index: 1556467 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.9383. Min Act: -0.0001
Data Index: 1232651 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7187. Min Range: -2.7187
Max Act: 2.0291. Min Act: -0.0001
Data Index: 1353074 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7187. Min Range: -2.7187
Max Act: 2.1014. Min Act: -0.0001
Data Index: 934475 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.8495. Min Act: -0.0001
Data Index: 346273 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.9899. Min Act: -0.0001
Data Index: 1133501 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.8419. Min Act: -0.0001
Data Index: 993272 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.7991. Min Act: -0.0001
Data Index: 1497984 (Python Code)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.8033. Min Act: -0.0001
Data Index: 588972 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.9527. Min Act: -0.0001
Data Index: 1026215 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.8649. Min Act: -0.0001
Data Index: 5790 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.7686. Min Act: -0.0001
Data Index: 574490 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.8026. Min Act: -0.0001
Data Index: 136485 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.5298. Min Act: -0.0001
Data Index: 79312 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.7121. Min Act: -0.0001
Data Index: 343425 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7187. Min Range: -2.7187
Max Act: 1.8493. Min Act: -0.0001
Data Index: 85324 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19