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

Dataset: The Pile

Neuron 2678 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: 0.5920. Min Range: -0.5920

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1120697 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5182. Min Act: -0.0000

Data Index: 18236 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1430548 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1500525 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5191. Min Act: -0.0000

Data Index: 135782 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1764089 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5062. Min Act: -0.0000

Data Index: 119414 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1575418 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1982867 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4903. Min Act: -0.0000

Data Index: 948453 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1945711 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1996044 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4371. Min Act: -0.0000

Data Index: 779915 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4653. Min Act: -0.0000

Data Index: 621287 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1537878 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1860522 (The Pile)

Max Activating Token Index: 584

Text #16

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1359197 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1750493 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4058. Min Act: -0.0000

Data Index: 303843 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.4222. Min Act: -0.0000

Data Index: 981566 (The Pile)

Max Activating Token Index: 825