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

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

Neuron 4072 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0227. Min Act: -0.0002

Data Index: 659085 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0226. Min Act: -0.0002

Data Index: 655348 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1626422 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0221. Min Act: -0.0002

Data Index: 367740 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0220. Min Act: -0.0002

Data Index: 591924 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0217. Min Act: -0.0002

Data Index: 296425 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0212. Min Act: -0.0002

Data Index: 265499 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1615791 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1446686 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0210. Min Act: -0.0002

Data Index: 75795 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1646700 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0209. Min Act: -0.0002

Data Index: 298153 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1451858 (Python Code)

Max Activating Token Index: 341

Text #13

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1510960 (Python Code)

Max Activating Token Index: 945

Text #14

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1479835 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1546334 (Python Code)

Max Activating Token Index: 516

Text #16

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1566282 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1485411 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1513267 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1648025 (Python Code)

Max Activating Token Index: 18