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

Dataset: The Pile

Neuron 3133 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: 1.5173. Min Range: -1.5173

Max Act: 1.5173. Min Act: -0.0000

Data Index: 381340 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.4530. Min Act: -0.0000

Data Index: 1265418 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.4871. Min Act: -0.0000

Data Index: 1911592 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.3326. Min Act: -0.0000

Data Index: 764618 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.3543. Min Act: -0.0000

Data Index: 797627 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.2705. Min Act: -0.0000

Data Index: 885850 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1934332 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1501788 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1148637 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1203. Min Act: -0.0000

Data Index: 1466472 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1471705 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1943. Min Act: -0.0000

Data Index: 119974 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1458. Min Act: -0.0000

Data Index: 862756 (The Pile)

Max Activating Token Index: 967

Text #13

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.0801. Min Act: -0.0000

Data Index: 1069556 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1420. Min Act: -0.0000

Data Index: 116878 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1800854 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1456112 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.0605. Min Act: -0.0000

Data Index: 248334 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1570756 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 1.5173. Min Range: -1.5173

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1662229 (The Pile)

Max Activating Token Index: 337