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

Dataset: The Pile

Neuron 1566 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.7926. Min Act: -0.0000

Data Index: 1897967 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.4328. Min Act: -0.0000

Data Index: 1776712 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1540249 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.3824. Min Act: -0.0000

Data Index: 719726 (The Pile)

Max Activating Token Index: 889

Text #4

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.4636. Min Act: -0.0000

Data Index: 950165 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.4390. Min Act: -0.0000

Data Index: 364637 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.3788. Min Act: -0.0000

Data Index: 1305104 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.2720. Min Act: -0.0000

Data Index: 636055 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.2925. Min Act: -0.0000

Data Index: 604702 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.2724. Min Act: -0.0000

Data Index: 21559 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.2684. Min Act: -0.0000

Data Index: 17945 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.2078. Min Act: -0.0000

Data Index: 485700 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.1547. Min Act: -0.0000

Data Index: 531373 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.2416. Min Act: -0.0000

Data Index: 741506 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1714615 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1913614 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.1839. Min Act: -0.0000

Data Index: 114250 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1837209 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.1495. Min Act: -0.0000

Data Index: 748186 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 1.7926. Min Range: -1.7926

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1414928 (The Pile)

Max Activating Token Index: 601