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

Dataset: The Pile

Neuron 1125 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1946457 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0847. Min Act: -0.0000

Data Index: 881905 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0548. Min Act: 0.0000

Data Index: 783835 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.1888. Min Act: -0.0000

Data Index: 791759 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.1888. Min Range: -1.1888

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1041267 (The Pile)

Max Activating Token Index: 764

Text #5

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1551382 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.8187. Min Act: -0.0000

Data Index: 89163 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1983146 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.7271. Min Act: -0.0000

Data Index: 502654 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1242869 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1094495 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1029073 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.6407. Min Act: -0.0000

Data Index: 607795 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1525234 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1658264 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1172772 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1057393 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.5607. Min Act: -0.0000

Data Index: 658283 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.5417. Min Act: -0.0000

Data Index: 299507 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 1.1888. Min Range: -1.1888

Max Act: 0.5465. Min Act: -0.0000

Data Index: 739676 (The Pile)

Max Activating Token Index: 500