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

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

Neuron 4480 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.2164. Min Act: -0.0002

Data Index: 594814 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.2104. Min Act: -0.0002

Data Index: 295894 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1707. Min Act: -0.0002

Data Index: 966271 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1960. Min Act: -0.0002

Data Index: 643403 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1778. Min Act: -0.0002

Data Index: 731369 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1842. Min Act: -0.0002

Data Index: 1251367 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1661. Min Act: -0.0002

Data Index: 229168 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1513. Min Act: -0.0002

Data Index: 29828 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1468. Min Act: -0.0002

Data Index: 136842 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1299. Min Act: -0.0002

Data Index: 917550 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1208. Min Act: -0.0002

Data Index: 522438 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1329. Min Act: -0.0002

Data Index: 705491 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1224. Min Act: -0.0002

Data Index: 477595 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1177. Min Act: -0.0002

Data Index: 1241526 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1257. Min Act: -0.0002

Data Index: 701572 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1328. Min Act: -0.0002

Data Index: 181540 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1285. Min Act: -0.0002

Data Index: 751377 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1185. Min Act: -0.0002

Data Index: 392400 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1191. Min Act: -0.0002

Data Index: 232861 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.2164. Min Range: -0.2164

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1175160 (C4 (Web Text))

Max Activating Token Index: 330