Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2827 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1647. Min Act: -0.0001
Data Index: 1096876 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1610. Min Act: -0.0001
Data Index: 1346006 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1692. Min Act: -0.0001
Data Index: 810267 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1405. Min Act: -0.0001
Data Index: 914172 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1527. Min Act: -0.0001
Data Index: 1167814 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1349. Min Act: -0.0001
Data Index: 791196 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1292. Min Act: -0.0001
Data Index: 950576 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1341. Min Act: -0.0001
Data Index: 1333015 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1292. Min Act: -0.0001
Data Index: 256844 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1220. Min Act: -0.0001
Data Index: 411639 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1192. Min Act: -0.0001
Data Index: 1583263 (Python Code)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1193. Min Act: -0.0001
Data Index: 359543 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1258. Min Act: -0.0001
Data Index: 1021924 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1218. Min Act: -0.0001
Data Index: 589171 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1202. Min Act: -0.0001
Data Index: 1033998 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1178. Min Act: -0.0001
Data Index: 147985 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1155. Min Act: -0.0001
Data Index: 1207136 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1182. Min Act: -0.0001
Data Index: 1216590 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1104. Min Act: -0.0001
Data Index: 1636983 (Python Code)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1692. Min Range: -0.1692
Max Act: 0.1089. Min Act: -0.0001
Data Index: 330057 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19