Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2521 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1425. Min Act: -0.0001

Data Index: 123911 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1291. Min Act: -0.0001

Data Index: 32132 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1486. Min Act: -0.0001

Data Index: 648877 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1239614 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1363. Min Act: -0.0001

Data Index: 852217 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1193. Min Act: -0.0001

Data Index: 926365 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1241. Min Act: -0.0001

Data Index: 76912 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1169. Min Act: -0.0001

Data Index: 847704 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1261094 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1042487 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1085509 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1082. Min Act: -0.0001

Data Index: 484815 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1106. Min Act: -0.0001

Data Index: 751525 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1179. Min Act: -0.0001

Data Index: 688924 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1195. Min Act: -0.0001

Data Index: 31458 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1083. Min Act: -0.0001

Data Index: 917842 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1074305 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1141. Min Act: -0.0001

Data Index: 575313 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1273263 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1101. Min Act: -0.0001

Data Index: 607925 (C4 (Web Text))

Max Activating Token Index: 9