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

Dataset: The Pile

Neuron 738 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.4568. Min Act: -0.0000

Data Index: 967592 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.6251. Min Act: -0.0000

Data Index: 1111610 (The Pile)

Max Activating Token Index: 811

Text #2

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1634006 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.3922. Min Act: -0.0000

Data Index: 1851724 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.4673. Min Act: -0.0000

Data Index: 1317860 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.3135. Min Act: -0.0000

Data Index: 360065 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.2475. Min Act: -0.0000

Data Index: 56676 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.2303. Min Act: -0.0000

Data Index: 767232 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.3091. Min Act: -0.0000

Data Index: 48181 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.3035. Min Act: -0.0000

Data Index: 582649 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1849. Min Act: -0.0000

Data Index: 1381553 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1960. Min Act: -0.0000

Data Index: 296435 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.2082. Min Act: -0.0000

Data Index: 879007 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1142183 (The Pile)

Max Activating Token Index: 906

Text #14

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1252. Min Act: -0.0000

Data Index: 997840 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1292980 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1718858 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1513. Min Act: -0.0000

Data Index: 876515 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1163432 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 1.6251. Min Range: -1.6251

Max Act: 1.1873. Min Act: -0.0000

Data Index: 861488 (The Pile)

Max Activating Token Index: 298