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

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

Neuron 2099 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.3906. Min Act: -0.0000

Data Index: 800929 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 2.3906. Min Range: -2.3906

Max Act: 2.1014. Min Act: -0.0000

Data Index: 252839 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.9640. Min Act: -0.0000

Data Index: 781008 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.7707. Min Act: -0.0000

Data Index: 152393 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.8037. Min Act: -0.0000

Data Index: 863226 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.7200. Min Act: -0.0000

Data Index: 1246913 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.6088. Min Act: -0.0000

Data Index: 1118295 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.5437. Min Act: -0.0000

Data Index: 494926 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.5984. Min Act: -0.0000

Data Index: 887995 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.5087. Min Act: -0.0000

Data Index: 88489 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.5035. Min Act: -0.0000

Data Index: 422601 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.4985. Min Act: -0.0000

Data Index: 513328 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.4800. Min Act: -0.0000

Data Index: 1080440 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.3620. Min Act: -0.0000

Data Index: 1332159 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.4708. Min Act: -0.0000

Data Index: 968214 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.4069. Min Act: -0.0000

Data Index: 664389 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.4741. Min Act: -0.0000

Data Index: 161386 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.3125. Min Act: -0.0000

Data Index: 826997 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1298010 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 2.3906. Min Range: -2.3906

Max Act: 1.2912. Min Act: -0.0000

Data Index: 166218 (C4 (Web Text))

Max Activating Token Index: 492