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

Dataset: The Pile

Neuron 3847 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: 1.2834. Min Range: -1.2834

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1628848 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2340. Min Act: -0.0000

Data Index: 954385 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1322886 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1315872 (The Pile)

Max Activating Token Index: 714

Text #4

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1400872 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.1292. Min Act: -0.0000

Data Index: 82633 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1757089 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0813. Min Act: -0.0000

Data Index: 523610 (The Pile)

Max Activating Token Index: 328

Text #8

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0941. Min Act: -0.0000

Data Index: 332823 (The Pile)

Max Activating Token Index: 188

Text #9

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1436041 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1646497 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.1076. Min Act: -0.0000

Data Index: 76988 (The Pile)

Max Activating Token Index: 649

Text #12

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1997542 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.9634. Min Act: -0.0000

Data Index: 494323 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0800. Min Act: -0.0000

Data Index: 150416 (The Pile)

Max Activating Token Index: 988

Text #15

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.1389. Min Act: -0.0000

Data Index: 815248 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1935419 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.9892. Min Act: -0.0000

Data Index: 691635 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0116. Min Act: -0.0000

Data Index: 693905 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0014. Min Act: -0.0000

Data Index: 591162 (The Pile)

Max Activating Token Index: 380