Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 107 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1482. Min Act: -0.0002

Data Index: 467287 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1384. Min Act: -0.0002

Data Index: 335165 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1093181 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1405. Min Act: -0.0002

Data Index: 247920 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1382. Min Act: -0.0002

Data Index: 1164556 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1378. Min Act: -0.0001

Data Index: 1054456 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1337. Min Act: -0.0002

Data Index: 101680 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1274. Min Act: -0.0002

Data Index: 825173 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1259. Min Act: -0.0001

Data Index: 541020 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1164372 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1214999 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1266. Min Act: -0.0002

Data Index: 517168 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1287. Min Act: -0.0001

Data Index: 271126 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1007649 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1255. Min Act: -0.0002

Data Index: 467355 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1275. Min Act: -0.0002

Data Index: 401393 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1188. Min Act: -0.0002

Data Index: 478417 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1222. Min Act: -0.0001

Data Index: 316218 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1239. Min Act: -0.0001

Data Index: 143692 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1227. Min Act: -0.0002

Data Index: 171638 (C4 (Web Text))

Max Activating Token Index: 35