Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1933 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.8590. Min Act: -0.0001

Data Index: 803038 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7220. Min Act: -0.0001

Data Index: 1250851 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7215. Min Act: -0.0001

Data Index: 397757 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6752. Min Act: -0.0001

Data Index: 1203478 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.7192. Min Act: -0.0001

Data Index: 1606378 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6506. Min Act: -0.0001

Data Index: 292167 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6170. Min Act: -0.0001

Data Index: 712945 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6277. Min Act: -0.0001

Data Index: 110845 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6091. Min Act: -0.0001

Data Index: 1156705 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6079. Min Act: -0.0001

Data Index: 1352598 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6245. Min Act: -0.0001

Data Index: 217605 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6205. Min Act: -0.0001

Data Index: 1109369 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6236. Min Act: -0.0001

Data Index: 1482254 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.5946. Min Act: -0.0001

Data Index: 664441 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.5849. Min Act: -0.0001

Data Index: 390810 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6422. Min Act: -0.0001

Data Index: 35905 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.5882. Min Act: -0.0001

Data Index: 296868 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6120. Min Act: -0.0001

Data Index: 1640066 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.6204. Min Act: -0.0001

Data Index: 794761 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.8590. Min Range: -0.8590

Max Act: 0.5987. Min Act: -0.0001

Data Index: 323922 (C4 (Web Text))

Max Activating Token Index: 771