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

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

Neuron 3362 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: 2.7628. Min Range: -2.7628

Max Act: 2.7628. Min Act: -0.0000

Data Index: 543487 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.5648. Min Act: -0.0000

Data Index: 964503 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.3523. Min Act: -0.0000

Data Index: 1110515 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.3567. Min Act: -0.0000

Data Index: 578224 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.3068. Min Act: -0.0000

Data Index: 1022995 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.2559. Min Act: -0.0000

Data Index: 582697 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.2793. Min Act: -0.0000

Data Index: 146781 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.2453. Min Act: -0.0000

Data Index: 967562 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.1925. Min Act: -0.0000

Data Index: 688717 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.1891. Min Act: -0.0000

Data Index: 1193177 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.1628. Min Act: -0.0000

Data Index: 871354 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.0698. Min Act: -0.0000

Data Index: 280905 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.1250. Min Act: -0.0000

Data Index: 432928 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.1133. Min Act: -0.0000

Data Index: 1125898 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.1033. Min Act: -0.0000

Data Index: 1350863 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.0982. Min Act: -0.0000

Data Index: 392224 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.1080. Min Act: -0.0000

Data Index: 5419 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.0909. Min Act: -0.0000

Data Index: 1315393 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.0840. Min Act: -0.0000

Data Index: 516885 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 2.7628. Min Range: -2.7628

Max Act: 2.0960. Min Act: -0.0000

Data Index: 129227 (C4 (Web Text))

Max Activating Token Index: 462