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

Dataset: The Pile

Neuron 2989 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: 8.6692. Min Range: -8.6692

Max Act: 8.6692. Min Act: -0.0000

Data Index: 1367246 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.5233. Min Act: -0.0000

Data Index: 406270 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.2178. Min Act: -0.0000

Data Index: 868006 (The Pile)

Max Activating Token Index: 291

Text #3

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.5436. Min Act: -0.0000

Data Index: 846420 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 8.6692. Min Range: -8.6692

Max Act: 7.8849. Min Act: -0.0000

Data Index: 1175079 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.1443. Min Act: -0.0000

Data Index: 1403319 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 8.6692. Min Range: -8.6692

Max Act: 7.8000. Min Act: -0.0000

Data Index: 955933 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 8.6692. Min Range: -8.6692

Max Act: 7.5526. Min Act: -0.0000

Data Index: 1164770 (The Pile)

Max Activating Token Index: 768

Text #8

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.0006. Min Act: -0.0000

Data Index: 18451 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 8.6692. Min Range: -8.6692

Max Act: 7.8077. Min Act: -0.0000

Data Index: 1641405 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.2737. Min Act: -0.0000

Data Index: 1065735 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.5404. Min Act: -0.0000

Data Index: 1582488 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 8.6692. Min Range: -8.6692

Max Act: 7.9003. Min Act: -0.0000

Data Index: 203816 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.1775. Min Act: -0.0000

Data Index: 183501 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.4852. Min Act: -0.0000

Data Index: 292635 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 8.6692. Min Range: -8.6692

Max Act: 7.7565. Min Act: -0.0000

Data Index: 1078346 (The Pile)

Max Activating Token Index: 488

Text #16

Max Range: 8.6692. Min Range: -8.6692

Max Act: 7.8621. Min Act: -0.0000

Data Index: 1540097 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.1900. Min Act: -0.0000

Data Index: 1347268 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 8.6692. Min Range: -8.6692

Max Act: 8.0737. Min Act: -0.0000

Data Index: 1651124 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 8.6692. Min Range: -8.6692

Max Act: 7.7087. Min Act: -0.0000

Data Index: 1489510 (The Pile)

Max Activating Token Index: 625