Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2466 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0271. Min Act: -0.0002

Data Index: 588578 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0296. Min Act: -0.0002

Data Index: 787013 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1247562 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0266. Min Act: -0.0002

Data Index: 321489 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0275. Min Act: -0.0002

Data Index: 696651 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0256. Min Act: -0.0002

Data Index: 580788 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1111097 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0273. Min Act: -0.0002

Data Index: 339532 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0269. Min Act: -0.0002

Data Index: 786307 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0264. Min Act: -0.0002

Data Index: 579428 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1236551 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1303107 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0246. Min Act: -0.0002

Data Index: 292921 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0247. Min Act: -0.0002

Data Index: 544141 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0263. Min Act: -0.0002

Data Index: 165103 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0251. Min Act: -0.0002

Data Index: 605971 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1240881 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0253. Min Act: -0.0002

Data Index: 390055 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0237. Min Act: -0.0002

Data Index: 766967 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1277952 (C4 (Web Text))

Max Activating Token Index: 825