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

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

Neuron 3754 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1168285 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1342. Min Act: -0.0002

Data Index: 146733 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1305. Min Act: -0.0002

Data Index: 424457 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1172. Min Act: -0.0002

Data Index: 540500 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1281329 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1152. Min Act: -0.0002

Data Index: 638564 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1277. Min Act: -0.0002

Data Index: 671101 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1288. Min Act: -0.0002

Data Index: 467367 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1149975 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1324. Min Act: -0.0002

Data Index: 26526 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1065. Min Act: -0.0002

Data Index: 823384 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1173. Min Act: -0.0002

Data Index: 79359 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1143. Min Act: -0.0002

Data Index: 177649 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1228. Min Act: -0.0002

Data Index: 384034 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1115. Min Act: -0.0002

Data Index: 262305 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1117. Min Act: -0.0002

Data Index: 1321456 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1021. Min Act: -0.0002

Data Index: 108197 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1048. Min Act: -0.0002

Data Index: 597405 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1096. Min Act: -0.0002

Data Index: 416159 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1060794 (C4 (Web Text))

Max Activating Token Index: 123