Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4464 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7983. Min Act: -0.0003

Data Index: 1250071 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8227. Min Act: -0.0003

Data Index: 1033220 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7355. Min Act: -0.0002

Data Index: 1090626 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7363. Min Act: -0.0003

Data Index: 934121 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7553. Min Act: -0.0002

Data Index: 555176 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7064. Min Act: -0.0003

Data Index: 740026 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7281. Min Act: -0.0002

Data Index: 410550 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7294. Min Act: -0.0003

Data Index: 1017333 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7167. Min Act: -0.0002

Data Index: 837501 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7205. Min Act: -0.0002

Data Index: 1225167 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6900. Min Act: -0.0002

Data Index: 1000850 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7230. Min Act: -0.0003

Data Index: 33230 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6989. Min Act: -0.0003

Data Index: 606406 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7182. Min Act: -0.0003

Data Index: 389572 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6876. Min Act: -0.0002

Data Index: 532140 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7097. Min Act: -0.0002

Data Index: 419038 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6817. Min Act: -0.0002

Data Index: 999021 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6793. Min Act: -0.0003

Data Index: 823362 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6547. Min Act: -0.0002

Data Index: 24924 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6687. Min Act: -0.0003

Data Index: 969783 (C4 (Web Text))

Max Activating Token Index: 502