Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1266409 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2557. Min Act: -0.0001

Data Index: 462675 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1102653 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2295. Min Act: -0.0000

Data Index: 309059 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2379. Min Act: -0.0001

Data Index: 690403 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2269. Min Act: -0.0001

Data Index: 146823 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2333. Min Act: -0.0001

Data Index: 709556 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2241. Min Act: -0.0001

Data Index: 1198200 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2235. Min Act: -0.0001

Data Index: 798564 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1333227 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2204. Min Act: -0.0000

Data Index: 173784 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2196. Min Act: -0.0001

Data Index: 904464 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2331. Min Act: -0.0001

Data Index: 627207 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1196502 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1004045 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2157. Min Act: -0.0001

Data Index: 1355273 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2211. Min Act: -0.0001

Data Index: 598578 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2193. Min Act: -0.0001

Data Index: 212664 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2185. Min Act: -0.0001

Data Index: 1125779 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.2557. Min Range: -0.2557

Max Act: 0.2172. Min Act: -0.0001

Data Index: 421864 (C4 (Web Text))

Max Activating Token Index: 571