Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 824 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0001

Data Index: 102077 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0674. Min Act: -0.0002

Data Index: 226437 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1211663 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0644. Min Act: -0.0002

Data Index: 472913 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0662. Min Act: -0.0002

Data Index: 506913 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0609. Min Act: -0.0001

Data Index: 39318 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0629. Min Act: -0.0001

Data Index: 737776 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1167384 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0602. Min Act: -0.0002

Data Index: 138980 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0609. Min Act: -0.0002

Data Index: 262967 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0603. Min Act: -0.0002

Data Index: 398013 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0595. Min Act: -0.0002

Data Index: 957281 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0582. Min Act: -0.0001

Data Index: 357601 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1280541 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0599. Min Act: -0.0002

Data Index: 644803 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1148650 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1319734 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0576. Min Act: -0.0002

Data Index: 185692 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0564. Min Act: -0.0001

Data Index: 706972 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0574. Min Act: -0.0002

Data Index: 590171 (C4 (Web Text))

Max Activating Token Index: 422