Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4337 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.2843. Min Range: -3.2843
Max Act: 3.2843. Min Act: -0.0001
Data Index: 530766 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2843. Min Range: -3.2843
Max Act: 3.0828. Min Act: -0.0001
Data Index: 1102325 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.6854. Min Act: -0.0001
Data Index: 1326477 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.3374. Min Act: -0.0001
Data Index: 976990 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.2984. Min Act: -0.0001
Data Index: 1223537 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.5372. Min Act: -0.0001
Data Index: 218834 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.1713. Min Act: -0.0001
Data Index: 639547 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.4129. Min Act: -0.0001
Data Index: 434039 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.4002. Min Act: -0.0001
Data Index: 976966 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.5180. Min Act: -0.0001
Data Index: 486899 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.3872. Min Act: -0.0001
Data Index: 642230 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.2624. Min Act: -0.0001
Data Index: 1251422 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.2536. Min Act: -0.0001
Data Index: 1053673 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.2609. Min Act: -0.0001
Data Index: 171909 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.3376. Min Act: -0.0001
Data Index: 1343689 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.3329. Min Act: -0.0001
Data Index: 616880 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.4177. Min Act: -0.0001
Data Index: 1212515 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.3180. Min Act: -0.0001
Data Index: 418738 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.3218. Min Act: -0.0001
Data Index: 313592 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2843. Min Range: -3.2843
Max Act: 2.3105. Min Act: -0.0001
Data Index: 620776 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19