Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2012 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0262. Min Act: -0.0001

Data Index: 254710 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0275. Min Act: -0.0001

Data Index: 67792 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1580284 (Python Code)

Max Activating Token Index: 804

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1189540 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0261. Min Act: -0.0001

Data Index: 404402 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0251. Min Act: -0.0001

Data Index: 703564 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0246. Min Act: -0.0001

Data Index: 344100 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1111810 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0247. Min Act: -0.0001

Data Index: 153481 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0261. Min Act: -0.0001

Data Index: 467823 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0244. Min Act: -0.0001

Data Index: 367284 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0252. Min Act: -0.0001

Data Index: 1363440 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0262. Min Act: -0.0001

Data Index: 754878 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1333426 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0274. Min Act: -0.0001

Data Index: 36414 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0237. Min Act: -0.0001

Data Index: 593196 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1120792 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0251. Min Act: -0.0001

Data Index: 568337 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0247. Min Act: -0.0001

Data Index: 818036 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0247. Min Act: -0.0001

Data Index: 642459 (C4 (Web Text))

Max Activating Token Index: 142