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

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

Neuron 2580 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: 0.1429. Min Range: -0.1429

Max Act: 0.1401. Min Act: -0.0002

Data Index: 58641 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1429. Min Act: -0.0001

Data Index: 245257 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1259151 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1391. Min Act: -0.0002

Data Index: 460980 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1220. Min Act: -0.0002

Data Index: 448430 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1317. Min Act: -0.0002

Data Index: 628233 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1268. Min Act: -0.0002

Data Index: 173461 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1285864 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1142. Min Act: -0.0002

Data Index: 955287 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1268. Min Act: -0.0002

Data Index: 208383 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1347. Min Act: -0.0002

Data Index: 397241 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1222. Min Act: -0.0001

Data Index: 684499 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1196. Min Act: -0.0001

Data Index: 212246 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1154. Min Act: -0.0002

Data Index: 211197 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1261156 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1280. Min Act: -0.0002

Data Index: 272516 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1127. Min Act: -0.0002

Data Index: 491540 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1198. Min Act: -0.0002

Data Index: 526246 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1041. Min Act: -0.0001

Data Index: 893117 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1148. Min Act: -0.0002

Data Index: 273324 (C4 (Web Text))

Max Activating Token Index: 202