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

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

Neuron 1571 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: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0003

Data Index: 889921 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0766. Min Act: -0.0003

Data Index: 413630 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0758. Min Act: -0.0003

Data Index: 787489 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0774. Min Act: -0.0003

Data Index: 386020 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0747. Min Act: -0.0004

Data Index: 492361 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0736. Min Act: -0.0003

Data Index: 955082 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0747. Min Act: -0.0003

Data Index: 1320812 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0723. Min Act: -0.0003

Data Index: 872594 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0726. Min Act: -0.0004

Data Index: 398139 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0706. Min Act: -0.0003

Data Index: 192510 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0705. Min Act: -0.0003

Data Index: 596923 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0681. Min Act: -0.0003

Data Index: 810188 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1248317 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0698. Min Act: -0.0003

Data Index: 298351 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0659. Min Act: -0.0003

Data Index: 686619 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1291028 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0704. Min Act: -0.0003

Data Index: 110826 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0717. Min Act: -0.0004

Data Index: 124618 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0691. Min Act: -0.0004

Data Index: 759674 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0685. Min Act: -0.0003

Data Index: 134734 (C4 (Web Text))

Max Activating Token Index: 852