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

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

Neuron 4268 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0001

Data Index: 66959 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0302. Min Act: -0.0001

Data Index: 592829 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0266. Min Act: -0.0001

Data Index: 969351 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1452529 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1458401 (Python Code)

Max Activating Token Index: 318

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1592681 (Python Code)

Max Activating Token Index: 912

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1485590 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0239. Min Act: -0.0001

Data Index: 280431 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1206961 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1361076 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0210. Min Act: -0.0001

Data Index: 952871 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1604528 (Python Code)

Max Activating Token Index: 559

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0226. Min Act: -0.0001

Data Index: 408526 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1008524 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1613889 (Python Code)

Max Activating Token Index: 357

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0199. Min Act: -0.0001

Data Index: 173284 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0215. Min Act: -0.0001

Data Index: 660532 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1527420 (Python Code)

Max Activating Token Index: 374

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1594072 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1183366 (C4 (Web Text))

Max Activating Token Index: 962