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

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

Neuron 5255 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: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1235362 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0287. Min Act: -0.0002

Data Index: 944684 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0266. Min Act: -0.0002

Data Index: 981043 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0257. Min Act: -0.0002

Data Index: 426478 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0260. Min Act: -0.0002

Data Index: 54431 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0255. Min Act: -0.0002

Data Index: 540018 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0236. Min Act: -0.0002

Data Index: 59855 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0242. Min Act: -0.0002

Data Index: 847151 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1316077 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0227. Min Act: -0.0002

Data Index: 867766 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1290358 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0228. Min Act: -0.0002

Data Index: 816252 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1309387 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0216. Min Act: -0.0002

Data Index: 373608 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1070951 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0218. Min Act: -0.0002

Data Index: 627707 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0214. Min Act: -0.0002

Data Index: 616492 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0217. Min Act: -0.0002

Data Index: 647920 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0211. Min Act: -0.0002

Data Index: 586884 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0224. Min Act: -0.0002

Data Index: 435710 (C4 (Web Text))

Max Activating Token Index: 271