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

Dataset: The Pile

Neuron 17 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.6666. Min Act: -0.0000

Data Index: 640183 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.8010. Min Act: -0.0000

Data Index: 924206 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.6274. Min Act: -0.0000

Data Index: 19721 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.5783. Min Act: -0.0000

Data Index: 411678 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.3995. Min Act: -0.0000

Data Index: 107689 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.5724. Min Act: -0.0000

Data Index: 45420 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.3415. Min Act: -0.0000

Data Index: 949420 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.4887. Min Act: -0.0000

Data Index: 1736488 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.3206. Min Act: -0.0000

Data Index: 779626 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.4773. Min Act: -0.0000

Data Index: 499074 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.4716. Min Act: -0.0000

Data Index: 1577496 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.6031. Min Act: -0.0000

Data Index: 1035040 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.4725. Min Act: -0.0000

Data Index: 232970 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.5759. Min Act: -0.0000

Data Index: 420653 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.3598. Min Act: -0.0000

Data Index: 1507163 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.3771. Min Act: -0.0000

Data Index: 1777943 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.3170. Min Act: -0.0000

Data Index: 206444 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.3367. Min Act: -0.0000

Data Index: 1301913 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.2002. Min Act: -0.0000

Data Index: 1608428 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 3.8010. Min Range: -3.8010

Max Act: 3.3355. Min Act: -0.0000

Data Index: 468091 (The Pile)

Max Activating Token Index: 566