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

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

Neuron 1288 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: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0004

Data Index: 469797 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0244. Min Act: -0.0004

Data Index: 782856 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0216. Min Act: -0.0004

Data Index: 166397 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0220. Min Act: -0.0004

Data Index: 778579 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1347291 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0214. Min Act: -0.0004

Data Index: 915607 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0223. Min Act: -0.0004

Data Index: 648636 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0218. Min Act: -0.0004

Data Index: 192134 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0225. Min Act: -0.0004

Data Index: 535262 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0211. Min Act: -0.0004

Data Index: 671670 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0211. Min Act: -0.0004

Data Index: 954820 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0198. Min Act: -0.0004

Data Index: 813505 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0211. Min Act: -0.0004

Data Index: 966961 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0213. Min Act: -0.0004

Data Index: 467012 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0213. Min Act: -0.0004

Data Index: 465464 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0197. Min Act: -0.0004

Data Index: 1654832 (Python Code)

Max Activating Token Index: 280

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0212. Min Act: -0.0004

Data Index: 1047675 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0234. Min Act: -0.0004

Data Index: 856471 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0200. Min Act: -0.0004

Data Index: 896740 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0206. Min Act: -0.0004

Data Index: 1253611 (C4 (Web Text))

Max Activating Token Index: 298