Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2753 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.3217. Min Act: -0.0001
Data Index: 105421 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.3457. Min Act: -0.0001
Data Index: 225571 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.2744. Min Act: -0.0001
Data Index: 298776 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.2683. Min Act: -0.0001
Data Index: 230619 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.2154. Min Act: -0.0001
Data Index: 948528 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.2042. Min Act: -0.0001
Data Index: 268278 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.1781. Min Act: -0.0001
Data Index: 983546 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.1346. Min Act: -0.0001
Data Index: 1087058 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.3371. Min Act: -0.0001
Data Index: 938440 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3457. Min Range: -4.3457
Max Act: 3.8441. Min Act: -0.0001
Data Index: 565900 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.1147. Min Act: -0.0001
Data Index: 1186588 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3457. Min Range: -4.3457
Max Act: 3.8999. Min Act: -0.0001
Data Index: 226913 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3457. Min Range: -4.3457
Max Act: 3.7461. Min Act: -0.0001
Data Index: 712103 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3457. Min Range: -4.3457
Max Act: 3.9249. Min Act: -0.0001
Data Index: 942875 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.1058. Min Act: -0.0001
Data Index: 1166808 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3457. Min Range: -4.3457
Max Act: 3.9102. Min Act: -0.0001
Data Index: 1336062 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.0486. Min Act: -0.0001
Data Index: 868978 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3457. Min Range: -4.3457
Max Act: 3.9095. Min Act: -0.0001
Data Index: 337112 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3457. Min Range: -4.3457
Max Act: 4.0375. Min Act: -0.0001
Data Index: 493131 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3457. Min Range: -4.3457
Max Act: 3.7045. Min Act: -0.0001
Data Index: 448315 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19