Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3142 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1824. Min Act: -0.0001
Data Index: 61363 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1310. Min Act: -0.0001
Data Index: 412537 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1208. Min Act: -0.0001
Data Index: 265378 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1229. Min Act: -0.0001
Data Index: 1136797 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1155. Min Act: -0.0001
Data Index: 341486 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1169. Min Act: -0.0001
Data Index: 1276580 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1155. Min Act: -0.0001
Data Index: 1063069 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1163. Min Act: -0.0001
Data Index: 1148207 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1110. Min Act: -0.0001
Data Index: 1273647 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1102. Min Act: -0.0001
Data Index: 652771 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1128. Min Act: -0.0001
Data Index: 710081 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1021. Min Act: -0.0001
Data Index: 1047423 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1117. Min Act: -0.0001
Data Index: 1256615 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1005. Min Act: -0.0001
Data Index: 643013 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1091. Min Act: -0.0001
Data Index: 177453 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1031. Min Act: -0.0001
Data Index: 553280 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1021. Min Act: -0.0001
Data Index: 255368 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.0976. Min Act: -0.0001
Data Index: 1020323 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1087. Min Act: -0.0001
Data Index: 392428 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1824. Min Range: -0.1824
Max Act: 0.1045. Min Act: -0.0001
Data Index: 969658 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19