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

Dataset: The Pile

Neuron 954 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: 0.2891. Min Range: -0.2891

Max Act: 0.2891. Min Act: -0.0000

Data Index: 117484 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1514099 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1728688 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1284589 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2238. Min Act: -0.0000

Data Index: 719283 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1594432 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2270. Min Act: -0.0000

Data Index: 508422 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2160. Min Act: -0.0000

Data Index: 649917 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1864417 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2613. Min Act: -0.0000

Data Index: 221213 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1065405 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1656. Min Act: -0.0000

Data Index: 117937 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2395. Min Act: -0.0000

Data Index: 387611 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1327483 (The Pile)

Max Activating Token Index: 318

Text #14

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1326906 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.2059. Min Act: -0.0000

Data Index: 455941 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1960. Min Act: -0.0000

Data Index: 358544 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1912722 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1776. Min Act: -0.0000

Data Index: 451720 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 0.2891. Min Range: -0.2891

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1120196 (The Pile)

Max Activating Token Index: 41