Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5054 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1123321 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1262. Min Act: -0.0002

Data Index: 214886 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1304. Min Act: -0.0002

Data Index: 161122 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1283. Min Act: -0.0002

Data Index: 1244516 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1130222 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1228. Min Act: -0.0002

Data Index: 816303 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1313. Min Act: -0.0002

Data Index: 959889 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1312. Min Act: -0.0002

Data Index: 269609 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1212851 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1262. Min Act: -0.0002

Data Index: 371509 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1152729 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1272. Min Act: -0.0002

Data Index: 372884 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1061623 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1208. Min Act: -0.0002

Data Index: 1310768 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1205. Min Act: -0.0002

Data Index: 961509 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1242. Min Act: -0.0002

Data Index: 742872 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1155497 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1023040 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1139. Min Act: -0.0002

Data Index: 118654 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1211101 (C4 (Web Text))

Max Activating Token Index: 20