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

Dataset: The Pile

Neuron 1960 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1910. Min Range: -2.1910

Max Act: 2.1238. Min Act: -0.0000

Data Index: 694295 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.9242. Min Act: -0.0000

Data Index: 1237619 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 2.1910. Min Range: -2.1910

Max Act: 2.1910. Min Act: -0.0000

Data Index: 772750 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.8660. Min Act: -0.0000

Data Index: 1693617 (The Pile)

Max Activating Token Index: 879

Text #4

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.9292. Min Act: -0.0000

Data Index: 1886124 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.9679. Min Act: -0.0000

Data Index: 374495 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6216. Min Act: -0.0000

Data Index: 885125 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6608. Min Act: -0.0000

Data Index: 1580015 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.7055. Min Act: -0.0000

Data Index: 1646729 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.4467. Min Act: -0.0000

Data Index: 322299 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1705909 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.5456. Min Act: -0.0000

Data Index: 1522517 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.5613. Min Act: -0.0000

Data Index: 1383310 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6226. Min Act: -0.0000

Data Index: 544848 (The Pile)

Max Activating Token Index: 885

Text #14

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1810672 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.5486. Min Act: -0.0000

Data Index: 78638 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1906833 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1726511 (The Pile)

Max Activating Token Index: 973

Text #18

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1858444 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 2.1910. Min Range: -2.1910

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1470316 (The Pile)

Max Activating Token Index: 368