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

Dataset: The Pile

Neuron 3937 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1960874 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3761. Min Act: -0.0000

Data Index: 286382 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1299734 (The Pile)

Max Activating Token Index: 55

Text #3

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3480. Min Act: -0.0000

Data Index: 29179 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1719698 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1613707 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1845419 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1091663 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1215016 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1150399 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2786. Min Act: -0.0000

Data Index: 77044 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1305124 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1969049 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1888873 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3227. Min Act: -0.0000

Data Index: 354589 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3181. Min Act: -0.0000

Data Index: 165917 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1036953 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1055637 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1319440 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1555705 (The Pile)

Max Activating Token Index: 708