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

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

Neuron 5278 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: 0.0471. Min Range: -0.0471

Max Act: 0.0471. Min Act: -0.0002

Data Index: 310833 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0333. Min Act: -0.0002

Data Index: 826538 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0308. Min Act: -0.0002

Data Index: 508921 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1351207 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0313. Min Act: -0.0002

Data Index: 439246 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0308. Min Act: -0.0002

Data Index: 890328 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1269846 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1587485 (Python Code)

Max Activating Token Index: 588

Text #8

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0284. Min Act: -0.0002

Data Index: 134211 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0291. Min Act: -0.0002

Data Index: 703024 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1592119 (Python Code)

Max Activating Token Index: 645

Text #11

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0273. Min Act: -0.0002

Data Index: 989238 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0271. Min Act: -0.0002

Data Index: 717010 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0272. Min Act: -0.0002

Data Index: 317871 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0251. Min Act: -0.0002

Data Index: 664514 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0259. Min Act: -0.0002

Data Index: 27511 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0253. Min Act: -0.0002

Data Index: 601059 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1012024 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0252. Min Act: -0.0002

Data Index: 468288 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0243. Min Act: -0.0002

Data Index: 553380 (C4 (Web Text))

Max Activating Token Index: 498