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

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

Neuron 3702 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: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0002

Data Index: 72091 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0599. Min Act: -0.0002

Data Index: 310682 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0586. Min Act: -0.0002

Data Index: 113572 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0556. Min Act: -0.0002

Data Index: 345779 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0593. Min Act: -0.0002

Data Index: 440863 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1118021 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0570. Min Act: -0.0002

Data Index: 907022 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0578. Min Act: -0.0002

Data Index: 187966 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0514. Min Act: -0.0002

Data Index: 701443 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0496. Min Act: -0.0002

Data Index: 988269 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0556. Min Act: -0.0002

Data Index: 9526 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0554. Min Act: -0.0002

Data Index: 169 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0509. Min Act: -0.0002

Data Index: 894825 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0527. Min Act: -0.0002

Data Index: 808234 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0512. Min Act: -0.0002

Data Index: 378039 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0495. Min Act: -0.0002

Data Index: 975467 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1314680 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1243544 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1149729 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0503. Min Act: -0.0002

Data Index: 219408 (C4 (Web Text))

Max Activating Token Index: 354