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

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

Neuron 1444 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: 0.1708. Min Range: -0.1708

Max Act: 0.1708. Min Act: -0.0001

Data Index: 891994 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1494. Min Act: -0.0001

Data Index: 31814 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1433. Min Act: -0.0002

Data Index: 581437 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1426. Min Act: -0.0001

Data Index: 436327 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1185442 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1384. Min Act: -0.0002

Data Index: 71436 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1085054 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1270. Min Act: -0.0002

Data Index: 390879 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1268. Min Act: -0.0002

Data Index: 659575 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1086. Min Act: -0.0002

Data Index: 543109 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1343. Min Act: -0.0002

Data Index: 424000 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1302. Min Act: -0.0001

Data Index: 151709 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1176. Min Act: -0.0002

Data Index: 840039 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1001812 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1187. Min Act: -0.0001

Data Index: 604186 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1203. Min Act: -0.0001

Data Index: 1575050 (Python Code)

Max Activating Token Index: 833

Text #16

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1209. Min Act: -0.0001

Data Index: 612702 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1170. Min Act: -0.0001

Data Index: 818886 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1078759 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.1708. Min Range: -0.1708

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1549632 (Python Code)

Max Activating Token Index: 355