Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3304 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1214626 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1321. Min Act: -0.0000

Data Index: 283096 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1312. Min Act: -0.0000

Data Index: 823599 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1297. Min Act: -0.0000

Data Index: 678116 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1264. Min Act: -0.0000

Data Index: 439661 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1272. Min Act: -0.0000

Data Index: 907049 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1308. Min Act: -0.0000

Data Index: 204071 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1175. Min Act: -0.0000

Data Index: 292931 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1161. Min Act: -0.0000

Data Index: 553808 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1238. Min Act: -0.0000

Data Index: 625542 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1231. Min Act: -0.0000

Data Index: 574993 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1190. Min Act: -0.0000

Data Index: 344340 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1306816 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1220. Min Act: -0.0000

Data Index: 259430 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1214. Min Act: -0.0000

Data Index: 685377 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1127. Min Act: -0.0000

Data Index: 450485 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1292232 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1243. Min Act: -0.0000

Data Index: 607349 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1150. Min Act: -0.0000

Data Index: 446339 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1262572 (C4 (Web Text))

Max Activating Token Index: 419