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

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

Neuron 2811 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 358446 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0350. Min Act: -0.0002

Data Index: 765347 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0338. Min Act: -0.0002

Data Index: 270030 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0303. Min Act: -0.0003

Data Index: 43093 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0287. Min Act: -0.0002

Data Index: 242095 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0277. Min Act: -0.0003

Data Index: 605678 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0277. Min Act: -0.0002

Data Index: 34504 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0260. Min Act: -0.0002

Data Index: 583791 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0263. Min Act: -0.0003

Data Index: 109490 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0264. Min Act: -0.0002

Data Index: 405349 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0253. Min Act: -0.0002

Data Index: 548536 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0244. Min Act: -0.0003

Data Index: 45155 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1251943 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1264055 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0240. Min Act: -0.0002

Data Index: 686842 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1202034 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0227. Min Act: -0.0002

Data Index: 75221 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1451463 (Python Code)

Max Activating Token Index: 1015

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0224. Min Act: -0.0002

Data Index: 23544 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0233. Min Act: -0.0002

Data Index: 7432 (C4 (Web Text))

Max Activating Token Index: 56