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

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

Neuron 3412 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: 0.1393. Min Range: -0.1393

Max Act: 0.1393. Min Act: -0.0001

Data Index: 691498 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1348. Min Act: -0.0001

Data Index: 380232 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1294. Min Act: -0.0001

Data Index: 114527 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1212. Min Act: -0.0001

Data Index: 139432 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1196284 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1158. Min Act: -0.0001

Data Index: 479297 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1197. Min Act: -0.0001

Data Index: 276406 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1141. Min Act: -0.0002

Data Index: 652063 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1171. Min Act: -0.0001

Data Index: 609845 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1156. Min Act: -0.0001

Data Index: 613079 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1333387 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1141. Min Act: -0.0001

Data Index: 698819 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1122. Min Act: -0.0001

Data Index: 956977 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1168. Min Act: -0.0002

Data Index: 95581 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1072857 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1114. Min Act: -0.0002

Data Index: 888032 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1069. Min Act: -0.0001

Data Index: 20356 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1101. Min Act: -0.0002

Data Index: 412450 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1101. Min Act: -0.0001

Data Index: 176481 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1128. Min Act: -0.0001

Data Index: 451488 (C4 (Web Text))

Max Activating Token Index: 941