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

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

Neuron 3432 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1521. Min Act: -0.0001

Data Index: 595289 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1001555 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1381. Min Act: -0.0001

Data Index: 569309 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1403. Min Act: -0.0001

Data Index: 466345 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1354. Min Act: -0.0001

Data Index: 965488 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1351. Min Act: -0.0001

Data Index: 604484 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1321. Min Act: -0.0001

Data Index: 37088 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1339. Min Act: -0.0001

Data Index: 122774 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1327. Min Act: -0.0001

Data Index: 530960 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1275. Min Act: -0.0001

Data Index: 267605 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1162198 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1223. Min Act: -0.0001

Data Index: 604797 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1348915 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1283. Min Act: -0.0001

Data Index: 765361 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1272. Min Act: -0.0001

Data Index: 16389 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1336880 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1227. Min Act: -0.0001

Data Index: 613926 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1299. Min Act: -0.0001

Data Index: 970868 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1216. Min Act: -0.0001

Data Index: 418194 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1221. Min Act: -0.0001

Data Index: 900866 (C4 (Web Text))

Max Activating Token Index: 85