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

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

Neuron 1572 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: 0.0724. Min Range: -0.0724

Max Act: 0.0714. Min Act: -0.0004

Data Index: 741905 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0724. Min Act: -0.0003

Data Index: 836514 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1196603 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0691. Min Act: -0.0002

Data Index: 580854 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0692. Min Act: -0.0003

Data Index: 205220 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0691. Min Act: -0.0003

Data Index: 1049794 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1095144 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0637. Min Act: -0.0003

Data Index: 570569 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0580. Min Act: -0.0002

Data Index: 339929 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0623. Min Act: -0.0004

Data Index: 210520 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1515920 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1237357 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1241262 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0574. Min Act: -0.0003

Data Index: 906075 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0587. Min Act: -0.0003

Data Index: 607778 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0584. Min Act: -0.0003

Data Index: 808803 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1120832 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0569. Min Act: -0.0003

Data Index: 316954 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0573. Min Act: -0.0003

Data Index: 891431 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0724. Min Range: -0.0724

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1197102 (C4 (Web Text))

Max Activating Token Index: 840