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

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

Neuron 2497 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: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0002

Data Index: 847325 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1468473 (Python Code)

Max Activating Token Index: 136

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0310. Min Act: -0.0002

Data Index: 896639 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1433448 (Python Code)

Max Activating Token Index: 104

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1649249 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1525515 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0252. Min Act: -0.0002

Data Index: 539210 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1125129 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1012383 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1387732 (Python Code)

Max Activating Token Index: 243

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0220. Min Act: -0.0002

Data Index: 118472 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1557091 (Python Code)

Max Activating Token Index: 231

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1444163 (Python Code)

Max Activating Token Index: 727

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1537595 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1573036 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0263. Min Act: -0.0002

Data Index: 328371 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0277. Min Act: -0.0002

Data Index: 67393 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0237. Min Act: -0.0002

Data Index: 11347 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1606156 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0235. Min Act: -0.0002

Data Index: 878939 (C4 (Web Text))

Max Activating Token Index: 682