Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 54 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.7779. Min Act: -0.0001
Data Index: 615991 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.6807. Min Act: -0.0001
Data Index: 1268638 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.6887. Min Act: -0.0001
Data Index: 1019844 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.3616. Min Act: -0.0001
Data Index: 516867 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.6494. Min Act: -0.0001
Data Index: 187652 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5574. Min Act: -0.0001
Data Index: 553924 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5404. Min Act: -0.0001
Data Index: 423857 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.6148. Min Act: -0.0001
Data Index: 1244216 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5574. Min Act: -0.0001
Data Index: 846921 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.4609. Min Act: -0.0001
Data Index: 259302 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5329. Min Act: -0.0001
Data Index: 714487 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5725. Min Act: -0.0001
Data Index: 646611 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5376. Min Act: -0.0001
Data Index: 258528 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5367. Min Act: -0.0001
Data Index: 636699 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.3840. Min Act: -0.0001
Data Index: 165707 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5352. Min Act: -0.0001
Data Index: 643467 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5374. Min Act: -0.0001
Data Index: 910404 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.4644. Min Act: -0.0001
Data Index: 872737 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5089. Min Act: -0.0001
Data Index: 1343808 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7779. Min Range: -1.7779
Max Act: 1.5209. Min Act: -0.0001
Data Index: 278169 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19