Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 591 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1399236 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1121966 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0639. Min Act: -0.0003

Data Index: 927759 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1600498 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0651. Min Act: -0.0002

Data Index: 237235 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0608. Min Act: -0.0002

Data Index: 396767 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0597. Min Act: -0.0002

Data Index: 366956 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0602. Min Act: -0.0002

Data Index: 976196 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1549605 (Python Code)

Max Activating Token Index: 854

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1391812 (Python Code)

Max Activating Token Index: 678

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0595. Min Act: -0.0002

Data Index: 917359 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0594. Min Act: -0.0003

Data Index: 273181 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0598. Min Act: -0.0003

Data Index: 590290 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0603. Min Act: -0.0003

Data Index: 487300 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0588. Min Act: -0.0002

Data Index: 622991 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0584. Min Act: -0.0003

Data Index: 500924 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1026286 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0572. Min Act: -0.0002

Data Index: 66421 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1352142 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0547. Min Act: -0.0002

Data Index: 263913 (C4 (Web Text))

Max Activating Token Index: 872