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

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

Neuron 2840 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.8193. Min Act: -0.0000

Data Index: 637848 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7621. Min Act: -0.0000

Data Index: 430899 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1285734 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.8119. Min Act: -0.0000

Data Index: 331869 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1277698 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.8248. Min Act: -0.0000

Data Index: 791407 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7563. Min Act: -0.0000

Data Index: 169192 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1190813 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7633. Min Act: -0.0000

Data Index: 385463 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1278057 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1087704 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7669. Min Act: -0.0000

Data Index: 47240 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1086696 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1288111 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.8024. Min Act: -0.0000

Data Index: 726167 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7349. Min Act: -0.0000

Data Index: 740887 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1043863 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7367. Min Act: -0.0000

Data Index: 155995 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7584. Min Act: -0.0000

Data Index: 485178 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7085. Min Act: -0.0000

Data Index: 866800 (C4 (Web Text))

Max Activating Token Index: 784