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

Dataset: The Pile

Neuron 3973 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.1351. Min Act: -0.0000

Data Index: 304359 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.1300. Min Act: -0.0000

Data Index: 520099 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1905571 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1156573 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1055266 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1950944 (The Pile)

Max Activating Token Index: 893

Text #6

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1140171 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 1.1351. Min Range: -1.1351

Max Act: 1.0002. Min Act: -0.0000

Data Index: 319882 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8663. Min Act: -0.0000

Data Index: 36389 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8709. Min Act: -0.0000

Data Index: 129838 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1002361 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7963. Min Act: -0.0000

Data Index: 24831 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7308. Min Act: -0.0000

Data Index: 695420 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7769. Min Act: -0.0000

Data Index: 296227 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1244146 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1403232 (The Pile)

Max Activating Token Index: 95

Text #16

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8085. Min Act: -0.0000

Data Index: 797418 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1574105 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1752782 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 1.1351. Min Range: -1.1351

Max Act: 0.7032. Min Act: -0.0000

Data Index: 684019 (The Pile)

Max Activating Token Index: 898