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

Dataset: The Pile

Neuron 2893 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4486. Min Act: -0.0000

Data Index: 972970 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4355. Min Act: -0.0000

Data Index: 775344 (The Pile)

Max Activating Token Index: 328

Text #2

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1837821 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4248. Min Act: -0.0000

Data Index: 899750 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1528490 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4129. Min Act: -0.0000

Data Index: 658781 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1137421 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3831. Min Act: -0.0000

Data Index: 570846 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1433402 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4109. Min Act: -0.0000

Data Index: 190320 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1527928 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.4153. Min Act: -0.0000

Data Index: 343471 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1856234 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1426242 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3372. Min Act: -0.0000

Data Index: 531507 (The Pile)

Max Activating Token Index: 455

Text #15

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1384490 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3652. Min Act: -0.0000

Data Index: 192777 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3517. Min Act: -0.0000

Data Index: 350833 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3527. Min Act: -0.0000

Data Index: 735123 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 0.4486. Min Range: -0.4486

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1964876 (The Pile)

Max Activating Token Index: 240