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

Dataset: The Pile

Neuron 3058 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: 1.4668. Min Range: -1.4668

Max Act: 1.4433. Min Act: -0.0000

Data Index: 1989885 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.3907. Min Act: -0.0000

Data Index: 1441914 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1921054 (The Pile)

Max Activating Token Index: 982

Text #3

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.4668. Min Act: -0.0000

Data Index: 21564 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1716. Min Act: -0.0000

Data Index: 983285 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2257. Min Act: -0.0000

Data Index: 995610 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1608. Min Act: -0.0000

Data Index: 842076 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1165083 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2120. Min Act: -0.0000

Data Index: 1640014 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1513. Min Act: -0.0000

Data Index: 1855713 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2619. Min Act: -0.0000

Data Index: 1610368 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1677324 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1821. Min Act: -0.0000

Data Index: 88201 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1917. Min Act: -0.0000

Data Index: 386942 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1647642 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1159. Min Act: -0.0000

Data Index: 1359328 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.0982. Min Act: -0.0000

Data Index: 964667 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1119008 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1636424 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 1.4668. Min Range: -1.4668

Max Act: 1.1586. Min Act: -0.0000

Data Index: 1126551 (The Pile)

Max Activating Token Index: 200