Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 287 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1466481 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1583618 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1730897 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5209. Min Act: -0.0000

Data Index: 729628 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1628745 (The Pile)

Max Activating Token Index: 633

Text #5

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1548305 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4333. Min Act: -0.0000

Data Index: 629769 (The Pile)

Max Activating Token Index: 869

Text #7

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1087600 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1992913 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1702608 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4661. Min Act: -0.0000

Data Index: 807926 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4695. Min Act: -0.0000

Data Index: 359971 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1619353 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1303783 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1797287 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4117. Min Act: -0.0000

Data Index: 997787 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4557. Min Act: -0.0000

Data Index: 187119 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1166647 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.4281. Min Act: -0.0000

Data Index: 219583 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 0.8180. Min Range: -0.8180

Max Act: 0.5043. Min Act: -0.0000

Data Index: 257023 (The Pile)

Max Activating Token Index: 506