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

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

Neuron 16 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: 0.0282. Min Range: -0.0282

Max Act: 0.0282. Min Act: -0.0002

Data Index: 528193 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1261490 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0261. Min Act: -0.0002

Data Index: 94047 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0256. Min Act: -0.0002

Data Index: 201604 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0236. Min Act: -0.0002

Data Index: 59101 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0242. Min Act: -0.0002

Data Index: 272733 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0234. Min Act: -0.0002

Data Index: 74587 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0002

Data Index: 949567 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1206705 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0226. Min Act: -0.0002

Data Index: 631771 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1279452 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1358164 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0221. Min Act: -0.0002

Data Index: 536264 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0227. Min Act: -0.0002

Data Index: 869728 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0222. Min Act: -0.0002

Data Index: 860172 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0218. Min Act: -0.0002

Data Index: 388246 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0229. Min Act: -0.0002

Data Index: 238312 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0214. Min Act: -0.0002

Data Index: 428964 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0217. Min Act: -0.0002

Data Index: 620360 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.0282. Min Range: -0.0282

Max Act: 0.0221. Min Act: -0.0002

Data Index: 368333 (C4 (Web Text))

Max Activating Token Index: 180