Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3888. Min Act: -0.0000

Data Index: 820961 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1235643 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.2893. Min Act: -0.0000

Data Index: 1784521 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1136615 (The Pile)

Max Activating Token Index: 346

Text #4

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1438987 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1950724 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.2392. Min Act: -0.0000

Data Index: 731853 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1702202 (The Pile)

Max Activating Token Index: 243

Text #8

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.1801. Min Act: -0.0000

Data Index: 1107048 (The Pile)

Max Activating Token Index: 886

Text #9

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.1832. Min Act: -0.0000

Data Index: 142982 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.2226. Min Act: -0.0000

Data Index: 667021 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.1080. Min Act: -0.0000

Data Index: 184913 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.1941. Min Act: -0.0000

Data Index: 827155 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1300105 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.2189. Min Act: -0.0000

Data Index: 855957 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.1363. Min Act: -0.0000

Data Index: 971285 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.0650. Min Act: -0.0000

Data Index: 923884 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.1172. Min Act: -0.0000

Data Index: 534230 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.0777. Min Act: -0.0000

Data Index: 282216 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.0729. Min Act: -0.0000

Data Index: 873524 (The Pile)

Max Activating Token Index: 266