Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3522 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.5589. Min Act: -0.0000

Data Index: 414668 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.2614. Min Act: -0.0000

Data Index: 1265976 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.3679. Min Act: -0.0000

Data Index: 514365 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.1819. Min Act: -0.0000

Data Index: 1187107 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.0787. Min Act: -0.0000

Data Index: 1043675 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.2565. Min Act: -0.0000

Data Index: 461869 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.9498. Min Act: -0.0000

Data Index: 13119 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.9647. Min Act: -0.0000

Data Index: 1012743 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.9290. Min Act: -0.0000

Data Index: 979776 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.7884. Min Act: -0.0000

Data Index: 254080 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.0645. Min Act: -0.0000

Data Index: 1032444 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.1899. Min Act: -0.0000

Data Index: 400260 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.8249. Min Act: -0.0000

Data Index: 656433 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.5002. Min Act: -0.0000

Data Index: 192985 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.5663. Min Act: -0.0000

Data Index: 150966 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.5447. Min Act: -0.0000

Data Index: 168310 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.6973. Min Act: -0.0000

Data Index: 1049053 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.5227. Min Act: -0.0000

Data Index: 143460 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.5323. Min Act: -0.0000

Data Index: 905766 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 4.5589. Min Range: -4.5589

Max Act: 3.5272. Min Act: -0.0000

Data Index: 429869 (C4 (Web Text))

Max Activating Token Index: 631