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

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

Neuron 2392 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.8249. Min Act: -0.0003

Data Index: 988888 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7916. Min Act: -0.0002

Data Index: 1170684 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7685. Min Act: -0.0003

Data Index: 106433 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.8145. Min Act: -0.0003

Data Index: 1108453 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7544. Min Act: -0.0003

Data Index: 357779 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7624. Min Act: -0.0003

Data Index: 1175476 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7375. Min Act: -0.0003

Data Index: 785582 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7572. Min Act: -0.0003

Data Index: 51120 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7210. Min Act: -0.0003

Data Index: 396442 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7644. Min Act: -0.0002

Data Index: 1160672 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7516. Min Act: -0.0003

Data Index: 78083 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7355. Min Act: -0.0002

Data Index: 288533 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7509. Min Act: -0.0003

Data Index: 283092 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7174. Min Act: -0.0002

Data Index: 701874 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7219. Min Act: -0.0003

Data Index: 634260 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7287. Min Act: -0.0003

Data Index: 169328 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7270. Min Act: -0.0003

Data Index: 1203690 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7097. Min Act: -0.0003

Data Index: 350804 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.7020. Min Act: -0.0003

Data Index: 1254204 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.8249. Min Range: -0.8249

Max Act: 0.6783. Min Act: -0.0003

Data Index: 394865 (C4 (Web Text))

Max Activating Token Index: 19