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

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

Neuron 851 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: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1352386 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0270. Min Act: -0.0002

Data Index: 273279 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0251. Min Act: -0.0002

Data Index: 726985 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1493248 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1529870 (Python Code)

Max Activating Token Index: 449

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0206. Min Act: -0.0002

Data Index: 936674 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1114739 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0207. Min Act: -0.0002

Data Index: 254165 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1324084 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1317542 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0203. Min Act: -0.0002

Data Index: 491871 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1039329 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0197. Min Act: -0.0002

Data Index: 572822 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0202. Min Act: -0.0002

Data Index: 721477 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1141390 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0186. Min Act: -0.0002

Data Index: 403213 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0192. Min Act: -0.0002

Data Index: 501954 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1578917 (Python Code)

Max Activating Token Index: 818

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0191. Min Act: -0.0002

Data Index: 377970 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0191. Min Act: -0.0002

Data Index: 606906 (C4 (Web Text))

Max Activating Token Index: 583