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

Dataset: The Pile

Neuron 2637 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: 0.7815. Min Range: -0.7815

Max Act: 0.7815. Min Act: -0.0000

Data Index: 958283 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7713. Min Act: -0.0000

Data Index: 177422 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6687. Min Act: -0.0000

Data Index: 211720 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6675. Min Act: -0.0000

Data Index: 629 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6253. Min Act: -0.0000

Data Index: 882092 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1705300 (The Pile)

Max Activating Token Index: 681

Text #6

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1760825 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6293. Min Act: -0.0000

Data Index: 209023 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1013334 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5955. Min Act: -0.0000

Data Index: 791966 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1830106 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1513798 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1973562 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4889. Min Act: -0.0000

Data Index: 349861 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5033. Min Act: -0.0000

Data Index: 317395 (The Pile)

Max Activating Token Index: 540

Text #15

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4978. Min Act: -0.0000

Data Index: 154507 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1844529 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4834. Min Act: -0.0000

Data Index: 778325 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1486655 (The Pile)

Max Activating Token Index: 805

Text #19

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1139235 (The Pile)

Max Activating Token Index: 824