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

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

Neuron 259 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0003

Data Index: 409572 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0253. Min Act: -0.0003

Data Index: 318660 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0246. Min Act: -0.0003

Data Index: 4171 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0227. Min Act: -0.0003

Data Index: 793048 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0226. Min Act: -0.0003

Data Index: 320350 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0226. Min Act: -0.0003

Data Index: 432048 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0225. Min Act: -0.0003

Data Index: 590913 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0213. Min Act: -0.0003

Data Index: 635634 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1143138 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0003

Data Index: 203954 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0003

Data Index: 111560 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0003

Data Index: 235789 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0003

Data Index: 575040 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0205. Min Act: -0.0003

Data Index: 852721 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0204. Min Act: -0.0003

Data Index: 6483 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0203. Min Act: -0.0002

Data Index: 599022 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0202. Min Act: -0.0003

Data Index: 170401 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0205. Min Act: -0.0003

Data Index: 822233 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0201. Min Act: -0.0003

Data Index: 527514 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0201. Min Act: -0.0003

Data Index: 637412 (C4 (Web Text))

Max Activating Token Index: 236