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

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

Neuron 3684 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0000

Data Index: 1448452 (Python Code)

Max Activating Token Index: 1007

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0304. Min Act: -0.0000

Data Index: 571069 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0295. Min Act: -0.0001

Data Index: 496249 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0274. Min Act: -0.0000

Data Index: 1424756 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0279. Min Act: -0.0000

Data Index: 1618761 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0275. Min Act: -0.0000

Data Index: 691669 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0281. Min Act: -0.0000

Data Index: 1341110 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0274. Min Act: -0.0000

Data Index: 1014503 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0268. Min Act: -0.0000

Data Index: 203349 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0265. Min Act: -0.0000

Data Index: 1533887 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0263. Min Act: -0.0000

Data Index: 94368 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0265. Min Act: -0.0000

Data Index: 1468509 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1211300 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1452416 (Python Code)

Max Activating Token Index: 336

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0260. Min Act: -0.0000

Data Index: 339089 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1450399 (Python Code)

Max Activating Token Index: 442

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1410069 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0248. Min Act: -0.0000

Data Index: 319538 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0235. Min Act: -0.0000

Data Index: 881095 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0249. Min Act: -0.0000

Data Index: 425407 (C4 (Web Text))

Max Activating Token Index: 670