Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1099 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0299. Min Act: -0.0003

Data Index: 290508 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1381688 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1636119 (Python Code)

Max Activating Token Index: 978

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0003

Data Index: 480085 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1025212 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0274. Min Act: -0.0002

Data Index: 910167 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0269. Min Act: -0.0002

Data Index: 985637 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0278. Min Act: -0.0003

Data Index: 501250 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1553374 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1401834 (Python Code)

Max Activating Token Index: 538

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1400332 (Python Code)

Max Activating Token Index: 825

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1433915 (Python Code)

Max Activating Token Index: 173

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1204383 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1450414 (Python Code)

Max Activating Token Index: 572

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1496314 (Python Code)

Max Activating Token Index: 845

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0236. Min Act: -0.0003

Data Index: 129841 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0210. Min Act: -0.0003

Data Index: 40221 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0237. Min Act: -0.0003

Data Index: 966937 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1584012 (Python Code)

Max Activating Token Index: 854

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0241. Min Act: -0.0003

Data Index: 370232 (C4 (Web Text))

Max Activating Token Index: 942