Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1727 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0259. Min Range: -2.0259
Max Act: 2.0259. Min Act: -0.0001
Data Index: 161587 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.7766. Min Act: -0.0001
Data Index: 830709 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.8482. Min Act: -0.0001
Data Index: 146850 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.7398. Min Act: -0.0001
Data Index: 670789 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.5989. Min Act: -0.0001
Data Index: 626421 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.4765. Min Act: -0.0001
Data Index: 1029949 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.4976. Min Act: -0.0001
Data Index: 400285 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.5153. Min Act: -0.0001
Data Index: 983704 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.4626. Min Act: -0.0001
Data Index: 193751 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.4006. Min Act: -0.0001
Data Index: 1287823 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.5115. Min Act: -0.0001
Data Index: 875967 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.4797. Min Act: -0.0001
Data Index: 19696 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.3829. Min Act: -0.0001
Data Index: 106796 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.3357. Min Act: -0.0001
Data Index: 906765 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.4200. Min Act: -0.0001
Data Index: 1335262 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.2959. Min Act: -0.0001
Data Index: 590028 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.3285. Min Act: -0.0001
Data Index: 582141 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.3222. Min Act: -0.0001
Data Index: 892632 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.3174. Min Act: -0.0001
Data Index: 716650 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0259. Min Range: -2.0259
Max Act: 1.3421. Min Act: -0.0001
Data Index: 313057 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19