Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 405 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.5797. Min Act: -0.0000

Data Index: 889526 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1923. Min Act: -0.0000

Data Index: 367732 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1150. Min Act: -0.0000

Data Index: 914146 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1678. Min Act: -0.0000

Data Index: 752564 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1027805 (The Pile)

Max Activating Token Index: 188

Text #5

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1557739 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1925866 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.8999. Min Act: -0.0000

Data Index: 885300 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1535520 (The Pile)

Max Activating Token Index: 855

Text #9

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1240025 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.9623. Min Act: -0.0000

Data Index: 254055 (The Pile)

Max Activating Token Index: 697

Text #11

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1294898 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1288620 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.9162. Min Act: -0.0000

Data Index: 322439 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.9226. Min Act: -0.0000

Data Index: 432200 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.8636. Min Act: -0.0000

Data Index: 937424 (The Pile)

Max Activating Token Index: 865

Text #16

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.8685. Min Act: -0.0000

Data Index: 1379322 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.8471. Min Act: -0.0000

Data Index: 648153 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.8549. Min Act: -0.0000

Data Index: 696589 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 1.5797. Min Range: -1.5797

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1636207 (The Pile)

Max Activating Token Index: 912