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

Dataset: The Pile

Neuron 4470 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: 0.5869. Min Range: -0.5869

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1738520 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1727291 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1391660 (The Pile)

Max Activating Token Index: 851

Text #3

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1690929 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3736. Min Act: -0.0000

Data Index: 91137 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.4167. Min Act: -0.0000

Data Index: 341189 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3819. Min Act: -0.0000

Data Index: 941324 (The Pile)

Max Activating Token Index: 319

Text #7

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1100021 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3561. Min Act: -0.0000

Data Index: 657822 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1002991 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1318543 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3296. Min Act: -0.0000

Data Index: 805315 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1022202 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3430. Min Act: -0.0000

Data Index: 779119 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1923032 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3499. Min Act: -0.0000

Data Index: 200818 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3216. Min Act: -0.0000

Data Index: 81582 (The Pile)

Max Activating Token Index: 310

Text #17

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3518. Min Act: -0.0000

Data Index: 470285 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3219. Min Act: -0.0000

Data Index: 289413 (The Pile)

Max Activating Token Index: 221

Text #19

Max Range: 0.5869. Min Range: -0.5869

Max Act: 0.3178. Min Act: -0.0000

Data Index: 936125 (The Pile)

Max Activating Token Index: 260