Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 44 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0227. Min Act: -0.0005

Data Index: 1435922 (Python Code)

Max Activating Token Index: 366

Text #1

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0226. Min Act: -0.0005

Data Index: 578624 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0218. Min Act: -0.0005

Data Index: 1279405 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0216. Min Act: -0.0005

Data Index: 9767 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0214. Min Act: -0.0005

Data Index: 298553 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0212. Min Act: -0.0005

Data Index: 1406707 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0197. Min Act: -0.0005

Data Index: 200486 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1141197 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1155448 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0199. Min Act: -0.0005

Data Index: 1329676 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0207. Min Act: -0.0005

Data Index: 304827 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0205. Min Act: -0.0005

Data Index: 749790 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0005

Data Index: 40716 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0207. Min Act: -0.0005

Data Index: 1380153 (Python Code)

Max Activating Token Index: 658

Text #14

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0005

Data Index: 1333132 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0203. Min Act: -0.0005

Data Index: 179256 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0201. Min Act: -0.0005

Data Index: 236832 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0005

Data Index: 1168258 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0212. Min Act: -0.0005

Data Index: 120503 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1145542 (C4 (Web Text))

Max Activating Token Index: 984