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

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

Neuron 3492 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0806. Min Range: -1.0806

Max Act: 1.0308. Min Act: -0.0000

Data Index: 959968 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.0806. Min Range: -1.0806

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1212499 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1026915 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1317723 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9911. Min Act: -0.0000

Data Index: 41259 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9866. Min Act: -0.0000

Data Index: 345286 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9297. Min Act: -0.0000

Data Index: 432294 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.0806. Min Range: -1.0806

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1176814 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9675. Min Act: -0.0000

Data Index: 173444 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9079. Min Act: -0.0000

Data Index: 558965 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.8957. Min Act: -0.0000

Data Index: 767452 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9481. Min Act: -0.0000

Data Index: 554651 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.8817. Min Act: -0.0000

Data Index: 1208576 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.8625. Min Act: -0.0000

Data Index: 98474 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.8585. Min Act: -0.0000

Data Index: 195987 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.8728. Min Act: -0.0000

Data Index: 868104 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.9132. Min Act: -0.0000

Data Index: 952091 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.8051. Min Act: -0.0000

Data Index: 499001 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1322707 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.0806. Min Range: -1.0806

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1352159 (C4 (Web Text))

Max Activating Token Index: 811