Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3722 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.4367. Min Range: -2.4367
Max Act: 2.4367. Min Act: -0.0001
Data Index: 131922 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4367. Min Range: -2.4367
Max Act: 2.0847. Min Act: -0.0001
Data Index: 341812 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4367. Min Range: -2.4367
Max Act: 2.3910. Min Act: -0.0001
Data Index: 262325 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4367. Min Range: -2.4367
Max Act: 2.2180. Min Act: -0.0001
Data Index: 1055530 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4367. Min Range: -2.4367
Max Act: 2.1059. Min Act: -0.0001
Data Index: 980259 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4367. Min Range: -2.4367
Max Act: 2.1614. Min Act: -0.0001
Data Index: 72515 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.8187. Min Act: -0.0001
Data Index: 663693 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.8759. Min Act: -0.0001
Data Index: 1183586 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.8859. Min Act: -0.0001
Data Index: 748465 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.7859. Min Act: -0.0001
Data Index: 845493 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.9344. Min Act: -0.0001
Data Index: 559704 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.7247. Min Act: -0.0001
Data Index: 784436 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.8797. Min Act: -0.0001
Data Index: 1412980 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.6418. Min Act: -0.0001
Data Index: 13197 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.9189. Min Act: -0.0001
Data Index: 1172129 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.6196. Min Act: -0.0001
Data Index: 693650 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.8044. Min Act: -0.0001
Data Index: 1309159 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.7096. Min Act: -0.0001
Data Index: 964405 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.8498. Min Act: -0.0001
Data Index: 755861 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4367. Min Range: -2.4367
Max Act: 1.5460. Min Act: -0.0001
Data Index: 1454951 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19