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

Dataset: The Pile

Neuron 4860 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1215228 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1369600 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1231297 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9551. Min Act: -0.0000

Data Index: 771773 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9219. Min Act: -0.0000

Data Index: 914614 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1543693 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7864. Min Act: -0.0000

Data Index: 110656 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1383553 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1345039 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1079386 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1437151 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1969357 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8007. Min Act: -0.0000

Data Index: 870229 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1076381 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7743. Min Act: -0.0000

Data Index: 71589 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7341. Min Act: -0.0000

Data Index: 663219 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1044915 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7231. Min Act: -0.0000

Data Index: 556180 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7690. Min Act: -0.0000

Data Index: 133772 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7702. Min Act: -0.0000

Data Index: 853037 (The Pile)

Max Activating Token Index: 502