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

Dataset: The Pile

Neuron 3683 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: 1.7837. Min Range: -1.7837

Max Act: 1.7837. Min Act: -0.0000

Data Index: 1301407 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.6533. Min Act: -0.0000

Data Index: 1699391 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.6042. Min Act: -0.0000

Data Index: 294614 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.5911. Min Act: -0.0000

Data Index: 1240106 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.6056. Min Act: -0.0000

Data Index: 512475 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1236737 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.3965. Min Act: -0.0000

Data Index: 1712556 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.4663. Min Act: -0.0000

Data Index: 452888 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.4374. Min Act: -0.0000

Data Index: 351020 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.4158. Min Act: -0.0000

Data Index: 362720 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1175993 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.2892. Min Act: -0.0000

Data Index: 972242 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.2450. Min Act: -0.0000

Data Index: 195156 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.2282. Min Act: -0.0000

Data Index: 263982 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.2989. Min Act: -0.0000

Data Index: 909835 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1606357 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1879013 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1627714 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.1796. Min Act: -0.0000

Data Index: 378545 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 1.7837. Min Range: -1.7837

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1419783 (The Pile)

Max Activating Token Index: 67