Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5717 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0243. Min Range: -1.0243

Max Act: 1.0243. Min Act: -0.0000

Data Index: 424985 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9951. Min Act: -0.0000

Data Index: 165969 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9503. Min Act: -0.0000

Data Index: 843988 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8624. Min Act: -0.0000

Data Index: 415964 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1246765 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8711. Min Act: -0.0000

Data Index: 258621 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9005. Min Act: -0.0000

Data Index: 729328 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8731. Min Act: -0.0000

Data Index: 314701 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1259491 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1007760 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8322. Min Act: -0.0000

Data Index: 69596 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8787. Min Act: -0.0000

Data Index: 962816 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8144. Min Act: -0.0000

Data Index: 426549 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1163252 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7849. Min Act: -0.0000

Data Index: 113952 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8244. Min Act: -0.0000

Data Index: 887495 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7632. Min Act: -0.0000

Data Index: 311880 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7891. Min Act: -0.0000

Data Index: 280684 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8192. Min Act: -0.0000

Data Index: 771030 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8417. Min Act: -0.0000

Data Index: 209879 (C4 (Web Text))

Max Activating Token Index: 361