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

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

Neuron 24 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: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0001

Data Index: 364741 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0272. Min Act: -0.0001

Data Index: 883211 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0272. Min Act: -0.0001

Data Index: 320193 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0240. Min Act: -0.0001

Data Index: 604195 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0248. Min Act: -0.0001

Data Index: 179922 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0241. Min Act: -0.0001

Data Index: 2432 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1358039 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0234. Min Act: -0.0001

Data Index: 778984 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1337175 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0230. Min Act: -0.0001

Data Index: 760295 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0215. Min Act: -0.0001

Data Index: 613351 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0230. Min Act: -0.0001

Data Index: 641036 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0231. Min Act: -0.0001

Data Index: 356435 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0230. Min Act: -0.0001

Data Index: 235175 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0181. Min Act: -0.0001

Data Index: 264690 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0209. Min Act: -0.0001

Data Index: 889416 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0220. Min Act: -0.0001

Data Index: 222637 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0211. Min Act: -0.0001

Data Index: 308225 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0215. Min Act: -0.0001

Data Index: 15231 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0213. Min Act: -0.0002

Data Index: 440486 (C4 (Web Text))

Max Activating Token Index: 28