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

Dataset: The Pile

Neuron 1001 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: 0.6559. Min Range: -0.6559

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1655194 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5707. Min Act: -0.0000

Data Index: 908879 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5210. Min Act: -0.0000

Data Index: 572333 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5193. Min Act: -0.0000

Data Index: 733586 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5616. Min Act: -0.0000

Data Index: 375425 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5285. Min Act: -0.0000

Data Index: 224438 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5278. Min Act: -0.0000

Data Index: 138762 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4753. Min Act: -0.0000

Data Index: 64769 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4584. Min Act: -0.0000

Data Index: 959085 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1132647 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1740610 (The Pile)

Max Activating Token Index: 581

Text #11

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4617. Min Act: -0.0000

Data Index: 991219 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1735485 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1049551 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4421. Min Act: -0.0000

Data Index: 793317 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1513986 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4206. Min Act: -0.0000

Data Index: 260880 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1745872 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1376517 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.4072. Min Act: -0.0000

Data Index: 931212 (The Pile)

Max Activating Token Index: 57