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

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

Neuron 1000 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: 0.1443. Min Range: -0.1443

Max Act: 0.1443. Min Act: -0.0003

Data Index: 967141 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1391. Min Act: -0.0003

Data Index: 1241491 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1419. Min Act: -0.0003

Data Index: 43388 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1343. Min Act: -0.0003

Data Index: 1290784 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1294. Min Act: -0.0003

Data Index: 261642 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1237. Min Act: -0.0003

Data Index: 592853 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1215. Min Act: -0.0003

Data Index: 288952 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1318. Min Act: -0.0003

Data Index: 141282 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1274. Min Act: -0.0003

Data Index: 510514 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1199. Min Act: -0.0003

Data Index: 892169 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1246. Min Act: -0.0003

Data Index: 220792 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1241. Min Act: -0.0003

Data Index: 137375 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1176. Min Act: -0.0003

Data Index: 1334392 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1186. Min Act: -0.0003

Data Index: 18097 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1228. Min Act: -0.0003

Data Index: 547531 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1225. Min Act: -0.0003

Data Index: 1133682 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1230. Min Act: -0.0003

Data Index: 281539 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1220. Min Act: -0.0003

Data Index: 357365 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1190. Min Act: -0.0003

Data Index: 524880 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.1443. Min Range: -0.1443

Max Act: 0.1179. Min Act: -0.0003

Data Index: 1050695 (C4 (Web Text))

Max Activating Token Index: 415