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

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

Neuron 2182 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: 0.1720. Min Range: -0.1720

Max Act: 0.1720. Min Act: -0.0003

Data Index: 43768 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1451. Min Act: -0.0003

Data Index: 349447 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1322. Min Act: -0.0003

Data Index: 488240 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1345. Min Act: -0.0003

Data Index: 223929 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1108. Min Act: -0.0003

Data Index: 450062 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1350. Min Act: -0.0003

Data Index: 57207 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1254. Min Act: -0.0003

Data Index: 332317 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1286. Min Act: -0.0003

Data Index: 696651 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1217. Min Act: -0.0003

Data Index: 1228513 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1270. Min Act: -0.0003

Data Index: 24418 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1178. Min Act: -0.0003

Data Index: 358275 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1226. Min Act: -0.0003

Data Index: 860469 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1139. Min Act: -0.0003

Data Index: 295477 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1170. Min Act: -0.0003

Data Index: 34881 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1158. Min Act: -0.0003

Data Index: 261549 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1199. Min Act: -0.0003

Data Index: 1215403 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1234. Min Act: -0.0003

Data Index: 225625 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1192. Min Act: -0.0003

Data Index: 744939 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1139. Min Act: -0.0003

Data Index: 1196163 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.1720. Min Range: -0.1720

Max Act: 0.1138. Min Act: -0.0003

Data Index: 1164780 (C4 (Web Text))

Max Activating Token Index: 268