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

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

Neuron 3398 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0760. Min Act: -0.0002

Data Index: 145962 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0649. Min Act: -0.0002

Data Index: 779483 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0746. Min Act: -0.0001

Data Index: 1061718 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0002

Data Index: 426586 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1258817 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0623. Min Act: -0.0001

Data Index: 672277 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0626. Min Act: -0.0001

Data Index: 870714 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0624. Min Act: -0.0002

Data Index: 201141 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1063258 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0576. Min Act: -0.0001

Data Index: 471271 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0661. Min Act: -0.0001

Data Index: 796466 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1139909 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1313965 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0538. Min Act: -0.0002

Data Index: 950736 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0623. Min Act: -0.0002

Data Index: 139528 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0553. Min Act: -0.0002

Data Index: 903701 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0590. Min Act: -0.0001

Data Index: 424007 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1358513 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0599. Min Act: -0.0001

Data Index: 887126 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0551. Min Act: -0.0002

Data Index: 595699 (C4 (Web Text))

Max Activating Token Index: 969