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

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

Neuron 81 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1198513 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1010. Min Act: -0.0000

Data Index: 764865 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0991. Min Act: -0.0000

Data Index: 466816 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1984 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1244164 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1232639 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0777. Min Act: -0.0000

Data Index: 473674 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0857. Min Act: -0.0000

Data Index: 574403 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0781. Min Act: -0.0000

Data Index: 340270 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0811. Min Act: -0.0000

Data Index: 491226 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0751. Min Act: -0.0000

Data Index: 155422 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1266613 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0750. Min Act: -0.0000

Data Index: 600924 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0770. Min Act: -0.0000

Data Index: 590597 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1123911 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1647876 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1551134 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0759. Min Act: -0.0000

Data Index: 967659 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0725. Min Act: -0.0000

Data Index: 490549 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1200689 (C4 (Web Text))

Max Activating Token Index: 100