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

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

Neuron 4532 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: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1031038 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1326947 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1253763 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0283. Min Act: -0.0002

Data Index: 165611 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1517160 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0259. Min Act: -0.0002

Data Index: 200923 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1051383 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0266. Min Act: -0.0002

Data Index: 153234 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0255. Min Act: -0.0002

Data Index: 45013 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0249. Min Act: -0.0002

Data Index: 904520 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0239. Min Act: -0.0002

Data Index: 459537 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1627530 (Python Code)

Max Activating Token Index: 208

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0242. Min Act: -0.0002

Data Index: 161271 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0246. Min Act: -0.0002

Data Index: 671540 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0244. Min Act: -0.0002

Data Index: 37950 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0254. Min Act: -0.0002

Data Index: 277004 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1495403 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0237. Min Act: -0.0002

Data Index: 105864 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1506199 (Python Code)

Max Activating Token Index: 341

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1102626 (C4 (Web Text))

Max Activating Token Index: 740