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

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

Neuron 4262 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1303473 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.8612. Min Act: -0.0000

Data Index: 446060 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.8425. Min Act: -0.0000

Data Index: 538344 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6995. Min Act: -0.0000

Data Index: 646115 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7443. Min Act: -0.0000

Data Index: 686075 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7260. Min Act: -0.0000

Data Index: 952204 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1045669 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1126772 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6900. Min Act: -0.0000

Data Index: 102602 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6907. Min Act: -0.0000

Data Index: 836305 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1093217 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6859. Min Act: -0.0000

Data Index: 637305 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6608. Min Act: -0.0000

Data Index: 944250 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7039. Min Act: -0.0000

Data Index: 82509 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6679. Min Act: -0.0000

Data Index: 240450 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6665. Min Act: -0.0000

Data Index: 966902 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6639. Min Act: -0.0000

Data Index: 753094 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6568. Min Act: -0.0000

Data Index: 111895 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6536. Min Act: -0.0000

Data Index: 379336 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6739. Min Act: -0.0000

Data Index: 662060 (C4 (Web Text))

Max Activating Token Index: 817