Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.7384. Min Act: -0.0000

Data Index: 904187 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1954789 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5454. Min Act: -0.0000

Data Index: 988845 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.7971. Min Act: -0.0000

Data Index: 570280 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5563. Min Act: -0.0000

Data Index: 1447262 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4242. Min Act: -0.0000

Data Index: 1568931 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4119. Min Act: -0.0000

Data Index: 38271 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1106971 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5147. Min Act: -0.0000

Data Index: 41387 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1509497 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3509. Min Act: -0.0000

Data Index: 310861 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1285162 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3604. Min Act: -0.0000

Data Index: 34690 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4193. Min Act: -0.0000

Data Index: 434000 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3265. Min Act: -0.0000

Data Index: 517802 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3902. Min Act: -0.0000

Data Index: 152410 (The Pile)

Max Activating Token Index: 4

Text #16

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3583. Min Act: -0.0000

Data Index: 494465 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3393. Min Act: -0.0000

Data Index: 966726 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1928424 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1965081 (The Pile)

Max Activating Token Index: 192