Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 726 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0229. Min Act: -0.0002
Data Index: 914916 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0228. Min Act: -0.0002
Data Index: 761705 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0228. Min Act: -0.0002
Data Index: 1027852 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0219. Min Act: -0.0002
Data Index: 685322 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0218. Min Act: -0.0002
Data Index: 36496 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0217. Min Act: -0.0002
Data Index: 28556 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0217. Min Act: -0.0002
Data Index: 651059 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0217. Min Act: -0.0002
Data Index: 1297346 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0217. Min Act: -0.0002
Data Index: 1054643 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0212. Min Act: -0.0002
Data Index: 671523 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0216. Min Act: -0.0002
Data Index: 1288342 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0216. Min Act: -0.0002
Data Index: 1072322 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0215. Min Act: -0.0002
Data Index: 774282 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0216. Min Act: -0.0002
Data Index: 86926 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0216. Min Act: -0.0002
Data Index: 833757 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0215. Min Act: -0.0002
Data Index: 617086 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0215. Min Act: -0.0002
Data Index: 115525 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0214. Min Act: -0.0002
Data Index: 304931 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0210. Min Act: -0.0002
Data Index: 965031 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0229. Min Range: -0.0229
Max Act: 0.0215. Min Act: -0.0002
Data Index: 192494 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19