Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 593 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2911. Min Act: -0.0001

Data Index: 1173762 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2782. Min Act: -0.0001

Data Index: 704989 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2991. Min Act: -0.0001

Data Index: 1124787 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2609. Min Act: -0.0001

Data Index: 337743 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2755. Min Act: -0.0001

Data Index: 706305 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2823. Min Act: -0.0001

Data Index: 28835 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2727. Min Act: -0.0001

Data Index: 993911 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2765. Min Act: -0.0001

Data Index: 381378 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2675. Min Act: -0.0001

Data Index: 643551 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2635. Min Act: -0.0001

Data Index: 898622 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2631. Min Act: -0.0001

Data Index: 542559 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2606. Min Act: -0.0001

Data Index: 362450 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2684. Min Act: -0.0001

Data Index: 546656 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2589. Min Act: -0.0001

Data Index: 710368 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1250077 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2521. Min Act: -0.0001

Data Index: 358872 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2478. Min Act: -0.0001

Data Index: 622591 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2453. Min Act: -0.0001

Data Index: 687001 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2279. Min Act: -0.0001

Data Index: 713553 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.2991. Min Range: -0.2991

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1093816 (C4 (Web Text))

Max Activating Token Index: 652