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

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

Neuron 2438 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1212485 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1147527 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0268. Min Act: -0.0003

Data Index: 215051 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0260. Min Act: -0.0003

Data Index: 663325 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1012697 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1123051 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0270. Min Act: -0.0003

Data Index: 106307 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1108600 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0244. Min Act: -0.0004

Data Index: 719131 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0241. Min Act: -0.0003

Data Index: 283887 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0261. Min Act: -0.0003

Data Index: 35895 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0244. Min Act: -0.0003

Data Index: 205774 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0248. Min Act: -0.0003

Data Index: 833010 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1319127 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1057507 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0239. Min Act: -0.0003

Data Index: 895318 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0255. Min Act: -0.0003

Data Index: 832369 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1030054 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0225. Min Act: -0.0003

Data Index: 65912 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0226. Min Act: -0.0004

Data Index: 805419 (C4 (Web Text))

Max Activating Token Index: 149