Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5300 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 22.1243. Min Range: -22.1243
Max Act: 22.1243. Min Act: -0.0001
Data Index: 1061569 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 22.1243. Min Range: -22.1243
Max Act: 18.1841. Min Act: -0.0001
Data Index: 1096758 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 22.1243. Min Range: -22.1243
Max Act: 15.7632. Min Act: -0.0001
Data Index: 942484 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 22.1243. Min Range: -22.1243
Max Act: 14.4699. Min Act: -0.0001
Data Index: 871918 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 22.1243. Min Range: -22.1243
Max Act: 14.6629. Min Act: -0.0001
Data Index: 134956 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 22.1243. Min Range: -22.1243
Max Act: 13.3329. Min Act: -0.0001
Data Index: 148998 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 22.1243. Min Range: -22.1243
Max Act: 11.4230. Min Act: -0.0001
Data Index: 1036914 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 22.1243. Min Range: -22.1243
Max Act: 6.5175. Min Act: -0.0001
Data Index: 478884 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 22.1243. Min Range: -22.1243
Max Act: 5.3259. Min Act: -0.0001
Data Index: 294545 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 22.1243. Min Range: -22.1243
Max Act: 4.4623. Min Act: -0.0001
Data Index: 172178 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 22.1243. Min Range: -22.1243
Max Act: 4.0482. Min Act: -0.0001
Data Index: 1308 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 22.1243. Min Range: -22.1243
Max Act: 3.6765. Min Act: -0.0001
Data Index: 1540841 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 22.1243. Min Range: -22.1243
Max Act: 4.2135. Min Act: -0.0001
Data Index: 1019358 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 22.1243. Min Range: -22.1243
Max Act: 2.5154. Min Act: -0.0001
Data Index: 1365577 (Python Code)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 22.1243. Min Range: -22.1243
Max Act: 3.0546. Min Act: -0.0001
Data Index: 1086003 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 22.1243. Min Range: -22.1243
Max Act: 1.5024. Min Act: -0.0001
Data Index: 1004838 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 22.1243. Min Range: -22.1243
Max Act: 2.4679. Min Act: -0.0001
Data Index: 388108 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 22.1243. Min Range: -22.1243
Max Act: 2.0755. Min Act: -0.0001
Data Index: 47461 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 22.1243. Min Range: -22.1243
Max Act: 1.0065. Min Act: -0.0001
Data Index: 349581 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 22.1243. Min Range: -22.1243
Max Act: 0.4812. Min Act: -0.0001
Data Index: 1067617 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19