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

Dataset: The Pile

Neuron 301 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: 1.3620. Min Range: -1.3620

Max Act: 1.2934. Min Act: -0.0000

Data Index: 1940123 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.3620. Min Act: -0.0000

Data Index: 364989 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1379145 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1309213 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.1194. Min Act: -0.0000

Data Index: 492706 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1871790 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.1699. Min Act: -0.0000

Data Index: 838761 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.1625. Min Act: -0.0000

Data Index: 45626 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.2126. Min Act: -0.0000

Data Index: 676800 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1933924 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.0054. Min Act: -0.0000

Data Index: 1257575 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1384482 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1918405 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.9816. Min Act: -0.0000

Data Index: 278943 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1686577 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.0282. Min Act: -0.0000

Data Index: 73159 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1812472 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 1.3620. Min Range: -1.3620

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1808852 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.0813. Min Act: -0.0000

Data Index: 1277128 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 1.3620. Min Range: -1.3620

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1911278 (The Pile)

Max Activating Token Index: 22