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

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

Neuron 796 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5270. Min Act: -0.0000

Data Index: 184302 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3996. Min Act: -0.0000

Data Index: 693406 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1211616 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3593. Min Act: -0.0000

Data Index: 79337 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3650. Min Act: -0.0000

Data Index: 934599 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3616. Min Act: -0.0000

Data Index: 615087 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3601. Min Act: -0.0000

Data Index: 230801 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3526. Min Act: -0.0000

Data Index: 530137 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3505. Min Act: -0.0000

Data Index: 684336 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3453. Min Act: -0.0000

Data Index: 574338 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3380. Min Act: -0.0000

Data Index: 563563 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3197. Min Act: -0.0000

Data Index: 829155 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3433. Min Act: -0.0000

Data Index: 279745 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3263. Min Act: -0.0000

Data Index: 474079 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3131. Min Act: -0.0000

Data Index: 608209 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3321. Min Act: -0.0000

Data Index: 406418 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1092953 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3198. Min Act: -0.0000

Data Index: 902320 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.2898. Min Act: -0.0000

Data Index: 33786 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.3088. Min Act: -0.0000

Data Index: 995389 (C4 (Web Text))

Max Activating Token Index: 263