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

Dataset: The Pile

Neuron 3015 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.7255. Min Act: -0.0000

Data Index: 996330 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.7302. Min Act: -0.0000

Data Index: 367829 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1523657 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1516253 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1241210 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5812. Min Act: -0.0000

Data Index: 688299 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6509. Min Act: -0.0000

Data Index: 383505 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1574769 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1062345 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5915. Min Act: -0.0001

Data Index: 503425 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5890. Min Act: -0.0000

Data Index: 700286 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6002. Min Act: 0.0001

Data Index: 450991 (The Pile)

Max Activating Token Index: 9

Text #12

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5865. Min Act: -0.0000

Data Index: 177218 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5864. Min Act: -0.0000

Data Index: 88286 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1086062 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1333834 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1375981 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5479. Min Act: 0.0001

Data Index: 95761 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5479. Min Act: -0.0000

Data Index: 338498 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5390. Min Act: -0.0000

Data Index: 824228 (The Pile)

Max Activating Token Index: 702