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

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

Neuron 1776 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1314961 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0332. Min Act: -0.0002

Data Index: 41501 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0323. Min Act: -0.0002

Data Index: 84912 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1038474 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0301. Min Act: -0.0002

Data Index: 224683 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0278. Min Act: -0.0002

Data Index: 885395 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1224326 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0274. Min Act: -0.0002

Data Index: 928578 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1409046 (Python Code)

Max Activating Token Index: 629

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0257. Min Act: -0.0002

Data Index: 313099 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0259. Min Act: -0.0002

Data Index: 255160 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0257. Min Act: -0.0002

Data Index: 816555 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1259332 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0258. Min Act: -0.0002

Data Index: 770409 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1362272 (Python Code)

Max Activating Token Index: 929

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0247. Min Act: -0.0002

Data Index: 758777 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0249. Min Act: -0.0002

Data Index: 947968 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0256. Min Act: -0.0002

Data Index: 413387 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1179500 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0241. Min Act: -0.0002

Data Index: 840654 (C4 (Web Text))

Max Activating Token Index: 29