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

Dataset: The Pile

Neuron 1787 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0000

Data Index: 885502 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2172. Min Act: -0.0000

Data Index: 878055 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1848. Min Act: -0.0000

Data Index: 156323 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1919. Min Act: -0.0000

Data Index: 779940 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1351983 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1498559 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1728. Min Act: -0.0000

Data Index: 719703 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1815460 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1551. Min Act: -0.0000

Data Index: 518852 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1313761 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1597484 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1720. Min Act: -0.0000

Data Index: 905816 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1529370 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1707. Min Act: -0.0000

Data Index: 896556 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1832906 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1261. Min Act: -0.0000

Data Index: 973150 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1079743 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1432. Min Act: -0.0000

Data Index: 944203 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1429405 (The Pile)

Max Activating Token Index: 365

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1355. Min Act: -0.0000

Data Index: 1480308 (The Pile)

Max Activating Token Index: 150