Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4216 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1579. Min Act: -0.0001
Data Index: 674866 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1272. Min Act: -0.0001
Data Index: 38389 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1355. Min Act: -0.0001
Data Index: 422834 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1348. Min Act: -0.0001
Data Index: 649910 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1297. Min Act: -0.0001
Data Index: 1359669 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1285. Min Act: -0.0001
Data Index: 945908 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1278. Min Act: -0.0001
Data Index: 1060987 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1193. Min Act: -0.0001
Data Index: 1317715 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1270. Min Act: -0.0001
Data Index: 467910 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1215. Min Act: -0.0001
Data Index: 341148 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1201. Min Act: -0.0001
Data Index: 681352 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1146. Min Act: -0.0001
Data Index: 1121871 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1099. Min Act: -0.0001
Data Index: 1124249 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1226. Min Act: -0.0001
Data Index: 266697 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1132. Min Act: -0.0001
Data Index: 1127665 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1163. Min Act: -0.0002
Data Index: 22767 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1117. Min Act: -0.0001
Data Index: 97206 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1111. Min Act: -0.0001
Data Index: 70827 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1123. Min Act: -0.0001
Data Index: 1283315 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1579. Min Range: -0.1579
Max Act: 0.1148. Min Act: -0.0001
Data Index: 1125251 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19