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

Dataset: The Pile

Neuron 4382 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: 0.9704. Min Range: -0.9704

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1449159 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7251. Min Act: -0.0000

Data Index: 376719 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7047. Min Act: -0.0000

Data Index: 498437 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6777. Min Act: -0.0000

Data Index: 384633 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7285. Min Act: -0.0000

Data Index: 28901 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1865258 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1289391 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7544. Min Act: -0.0000

Data Index: 394742 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6857. Min Act: -0.0000

Data Index: 543749 (The Pile)

Max Activating Token Index: 513

Text #9

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.7049. Min Act: -0.0000

Data Index: 966084 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1645243 (The Pile)

Max Activating Token Index: 407

Text #11

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1805626 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.5587. Min Act: -0.0000

Data Index: 846081 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6433. Min Act: -0.0000

Data Index: 886883 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6117. Min Act: -0.0000

Data Index: 772830 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6339. Min Act: -0.0000

Data Index: 58839 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1177927 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6574. Min Act: -0.0000

Data Index: 963147 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6583. Min Act: -0.0000

Data Index: 79075 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 0.9704. Min Range: -0.9704

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1256225 (The Pile)

Max Activating Token Index: 894