Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3418 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.4684. Min Act: -0.0000

Data Index: 1113179 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.3350. Min Act: -0.0000

Data Index: 897570 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1683. Min Act: -0.0000

Data Index: 730215 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.2905. Min Act: -0.0000

Data Index: 445063 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.4678. Min Act: -0.0000

Data Index: 1758605 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1447147 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1747895 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1342. Min Act: -0.0000

Data Index: 988160 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1240510 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1443735 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1284. Min Act: -0.0000

Data Index: 330853 (The Pile)

Max Activating Token Index: 694

Text #11

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1423254 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1698413 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1250. Min Act: -0.0000

Data Index: 738809 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1613. Min Act: -0.0000

Data Index: 228460 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1011250 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.0390. Min Act: -0.0000

Data Index: 893378 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1260312 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1482. Min Act: -0.0000

Data Index: 1052983 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 1.4684. Min Range: -1.4684

Max Act: 1.1162. Min Act: -0.0000

Data Index: 609599 (The Pile)

Max Activating Token Index: 757