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

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

Neuron 2120 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: 767768 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1480405 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0228. Min Act: -0.0003

Data Index: 614216 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1513799 (Python Code)

Max Activating Token Index: 724

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1455255 (Python Code)

Max Activating Token Index: 190

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1604423 (Python Code)

Max Activating Token Index: 157

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1375204 (Python Code)

Max Activating Token Index: 74

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1645000 (Python Code)

Max Activating Token Index: 513

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1489572 (Python Code)

Max Activating Token Index: 183

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1545995 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1481418 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1156857 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1544373 (Python Code)

Max Activating Token Index: 614

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0196. Min Act: -0.0003

Data Index: 851467 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1384796 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0213. Min Act: -0.0003

Data Index: 244082 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0203. Min Act: -0.0003

Data Index: 200124 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1523456 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1290198 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1350301 (C4 (Web Text))

Max Activating Token Index: 616