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

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

Neuron 2505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1407. Min Act: -0.0002

Data Index: 33494 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1503. Min Act: -0.0001

Data Index: 509195 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1402. Min Act: -0.0002

Data Index: 135188 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1350. Min Act: -0.0002

Data Index: 964637 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1213. Min Act: -0.0001

Data Index: 794970 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1239. Min Act: -0.0002

Data Index: 29468 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1294726 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1172. Min Act: -0.0002

Data Index: 451443 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1189. Min Act: -0.0001

Data Index: 804226 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1185. Min Act: -0.0001

Data Index: 668453 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1245476 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1149. Min Act: -0.0002

Data Index: 787919 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1195. Min Act: -0.0002

Data Index: 198417 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1167. Min Act: -0.0002

Data Index: 319667 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1137. Min Act: -0.0002

Data Index: 681464 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1146. Min Act: -0.0002

Data Index: 304566 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1099. Min Act: -0.0002

Data Index: 706616 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1102. Min Act: -0.0001

Data Index: 1228348 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1115. Min Act: -0.0002

Data Index: 184217 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1067. Min Act: -0.0002

Data Index: 43056 (C4 (Web Text))

Max Activating Token Index: 64