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

Dataset: The Pile

Neuron 4402 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1980877 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1612484 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1892501 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1670420 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5000. Min Act: -0.0000

Data Index: 564870 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1319437 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1010335 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1492551 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1338343 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4744. Min Act: -0.0000

Data Index: 158353 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1732391 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4455. Min Act: -0.0000

Data Index: 1834646 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1399845 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1415513 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4054. Min Act: -0.0000

Data Index: 432151 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4354. Min Act: 0.0000

Data Index: 1710115 (The Pile)

Max Activating Token Index: 605

Text #16

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4339. Min Act: -0.0000

Data Index: 515907 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1862352 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4037. Min Act: -0.0000

Data Index: 175491 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 0.5386. Min Range: -0.5386

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1029494 (The Pile)

Max Activating Token Index: 886