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

Dataset: The Pile

Neuron 2395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2087. Min Act: -0.0000

Data Index: 405719 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2263. Min Act: -0.0000

Data Index: 388561 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1868506 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1973. Min Act: -0.0000

Data Index: 305878 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2102. Min Act: -0.0000

Data Index: 789078 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2053. Min Act: -0.0000

Data Index: 563504 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1896. Min Act: -0.0000

Data Index: 289653 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1319317 (The Pile)

Max Activating Token Index: 787

Text #8

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1020467 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1849. Min Act: -0.0000

Data Index: 636871 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1913. Min Act: -0.0000

Data Index: 998909 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1755. Min Act: -0.0000

Data Index: 343703 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1862. Min Act: -0.0000

Data Index: 612418 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1920075 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1396186 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1737. Min Act: -0.0000

Data Index: 38499 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1401439 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1901571 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1571. Min Act: -0.0000

Data Index: 389009 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1543556 (The Pile)

Max Activating Token Index: 123