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

Dataset: The Pile

Neuron 2413 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1323775 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5684. Min Act: -0.0000

Data Index: 82470 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1143314 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5399. Min Act: -0.0000

Data Index: 47666 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5001. Min Act: -0.0000

Data Index: 612640 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5587. Min Act: -0.0000

Data Index: 471122 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1304819 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1468484 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1913830 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.5238. Min Act: -0.0000

Data Index: 886511 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4873. Min Act: -0.0000

Data Index: 798000 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4981. Min Act: -0.0000

Data Index: 733809 (The Pile)

Max Activating Token Index: 484

Text #12

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1468872 (The Pile)

Max Activating Token Index: 848

Text #13

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1251460 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1734949 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4818. Min Act: -0.0000

Data Index: 40119 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4117. Min Act: -0.0000

Data Index: 500209 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4660. Min Act: -0.0000

Data Index: 359969 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1838934 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.5929. Min Range: -0.5929

Max Act: 0.4739. Min Act: -0.0000

Data Index: 689721 (The Pile)

Max Activating Token Index: 510