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

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

Neuron 1329 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0954. Min Act: -0.0000

Data Index: 479826 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0887. Min Act: -0.0000

Data Index: 663718 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0783. Min Act: -0.0000

Data Index: 719052 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1011582 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0703. Min Act: -0.0000

Data Index: 503623 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0669. Min Act: -0.0000

Data Index: 648441 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0624. Min Act: -0.0000

Data Index: 605435 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0723. Min Act: -0.0000

Data Index: 518054 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1507020 (Python Code)

Max Activating Token Index: 745

Text #9

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1156199 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0659. Min Act: -0.0000

Data Index: 236874 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0680. Min Act: -0.0000

Data Index: 1214189 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1462341 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1169736 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1247711 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1210515 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0661. Min Act: -0.0000

Data Index: 314308 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1322323 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0688. Min Act: -0.0000

Data Index: 558419 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1432418 (Python Code)

Max Activating Token Index: 131