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

Dataset: The Pile

Neuron 2813 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3217. Min Act: -0.0000

Data Index: 493617 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1704218 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1038423 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1083828 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1253438 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1642968 (The Pile)

Max Activating Token Index: 520

Text #6

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1882982 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1828329 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1985323 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1916839 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1532054 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2716. Min Act: -0.0000

Data Index: 670660 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1287314 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1316777 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1399222 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2805. Min Act: -0.0000

Data Index: 641497 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2512. Min Act: -0.0000

Data Index: 852454 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1467975 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1992552 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2676. Min Act: -0.0000

Data Index: 55104 (The Pile)

Max Activating Token Index: 651