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

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

Neuron 690 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0235. Min Act: -0.0004

Data Index: 890121 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0004

Data Index: 314147 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0230. Min Act: -0.0004

Data Index: 1447762 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0244. Min Act: -0.0004

Data Index: 185443 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1467986 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1602576 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0224. Min Act: -0.0004

Data Index: 1080710 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0213. Min Act: -0.0004

Data Index: 211041 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1400459 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0213. Min Act: -0.0004

Data Index: 1390582 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1145695 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0200. Min Act: -0.0004

Data Index: 1601045 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0211. Min Act: -0.0004

Data Index: 573874 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0220. Min Act: -0.0004

Data Index: 1262058 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0207. Min Act: -0.0004

Data Index: 627984 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0195. Min Act: -0.0004

Data Index: 648367 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0179. Min Act: -0.0004

Data Index: 346383 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0204. Min Act: -0.0004

Data Index: 198142 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0207. Min Act: -0.0004

Data Index: 1103407 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0206. Min Act: -0.0004

Data Index: 1557588 (Python Code)

Max Activating Token Index: 973