Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3216 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0677. Min Act: -0.0002

Data Index: 491143 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1034581 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1095801 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0002

Data Index: 421644 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0562. Min Act: -0.0002

Data Index: 59117 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0611. Min Act: -0.0002

Data Index: 409851 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0556. Min Act: -0.0002

Data Index: 29225 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0576. Min Act: -0.0002

Data Index: 621755 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0582. Min Act: -0.0002

Data Index: 767719 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0589. Min Act: -0.0002

Data Index: 711313 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1246177 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0609. Min Act: -0.0002

Data Index: 586201 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0581. Min Act: -0.0002

Data Index: 815414 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0574. Min Act: -0.0002

Data Index: 283886 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0572. Min Act: -0.0002

Data Index: 613988 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1180513 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0530. Min Act: -0.0002

Data Index: 597404 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0571. Min Act: -0.0002

Data Index: 468363 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0531. Min Act: -0.0002

Data Index: 380779 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0563. Min Act: -0.0002

Data Index: 627456 (C4 (Web Text))

Max Activating Token Index: 472