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

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

Neuron 3257 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: 0.1417. Min Range: -0.1417

Max Act: 0.1417. Min Act: -0.0002

Data Index: 1192364 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1316869 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0980. Min Act: -0.0002

Data Index: 306398 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0891. Min Act: -0.0002

Data Index: 566302 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0873. Min Act: -0.0002

Data Index: 973004 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1148340 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1340576 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0799. Min Act: -0.0002

Data Index: 544192 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0828. Min Act: -0.0002

Data Index: 160711 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1295403 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1031372 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0830. Min Act: -0.0002

Data Index: 166899 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0786. Min Act: -0.0002

Data Index: 17376 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0749. Min Act: -0.0002

Data Index: 41070 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0777. Min Act: -0.0002

Data Index: 946259 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1177045 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0766. Min Act: -0.0002

Data Index: 185682 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1071919 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1275037 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.0767. Min Act: -0.0002

Data Index: 857985 (C4 (Web Text))

Max Activating Token Index: 894