Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2367 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.4528. Min Act: -0.0001
Data Index: 62780 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.3543. Min Act: -0.0001
Data Index: 629714 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.3235. Min Act: -0.0001
Data Index: 1056129 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.2026. Min Act: -0.0001
Data Index: 824197 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4528. Min Range: -2.4528
Max Act: 1.9727. Min Act: -0.0001
Data Index: 610646 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.0823. Min Act: -0.0001
Data Index: 1218192 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.1720. Min Act: -0.0001
Data Index: 1358481 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.1584. Min Act: -0.0001
Data Index: 325633 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.1500. Min Act: -0.0001
Data Index: 1103267 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.0383. Min Act: -0.0001
Data Index: 1129707 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.1169. Min Act: -0.0001
Data Index: 744285 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.2158. Min Act: -0.0001
Data Index: 688243 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.1013. Min Act: -0.0001
Data Index: 662086 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.1841. Min Act: -0.0001
Data Index: 186830 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.0594. Min Act: -0.0001
Data Index: 460519 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4528. Min Range: -2.4528
Max Act: 1.9899. Min Act: -0.0001
Data Index: 973858 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.1853. Min Act: -0.0001
Data Index: 287739 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4528. Min Range: -2.4528
Max Act: 1.9536. Min Act: -0.0001
Data Index: 1081740 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.1426. Min Act: -0.0001
Data Index: 219 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4528. Min Range: -2.4528
Max Act: 2.0272. Min Act: -0.0001
Data Index: 624513 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19