Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3490 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1007560 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1258609 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0739. Min Act: -0.0002

Data Index: 564131 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0704. Min Act: -0.0002

Data Index: 325817 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0713. Min Act: -0.0002

Data Index: 439297 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0712. Min Act: -0.0002

Data Index: 74120 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0653. Min Act: -0.0002

Data Index: 82922 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0661. Min Act: -0.0002

Data Index: 393198 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0675. Min Act: -0.0002

Data Index: 295024 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0633. Min Act: -0.0002

Data Index: 102239 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0604. Min Act: -0.0002

Data Index: 10245 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0600. Min Act: -0.0002

Data Index: 68673 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0615. Min Act: -0.0002

Data Index: 662641 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0610. Min Act: -0.0002

Data Index: 570030 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1326149 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0522. Min Act: -0.0002

Data Index: 714654 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1330543 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0494. Min Act: -0.0002

Data Index: 206351 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0470. Min Act: -0.0002

Data Index: 478309 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1189138 (C4 (Web Text))

Max Activating Token Index: 728