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

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

Neuron 2797 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: 0.0367. Min Range: -0.0367

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1199327 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0001

Data Index: 238315 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0356. Min Act: -0.0001

Data Index: 684483 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1151817 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0273. Min Act: -0.0001

Data Index: 21299 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1198965 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0253. Min Act: -0.0001

Data Index: 716350 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0267. Min Act: -0.0001

Data Index: 622421 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1450165 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0238. Min Act: -0.0001

Data Index: 1028737 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0260. Min Act: -0.0001

Data Index: 857968 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1046131 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1287796 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0257. Min Act: -0.0001

Data Index: 712726 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0248. Min Act: -0.0001

Data Index: 912243 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0256. Min Act: -0.0001

Data Index: 29897 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0248. Min Act: -0.0001

Data Index: 778088 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1203975 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1396526 (Python Code)

Max Activating Token Index: 289

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1022277 (C4 (Web Text))

Max Activating Token Index: 455