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

Dataset: The Pile

Neuron 3653 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.9892. Min Act: -0.0000

Data Index: 1037409 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.7660. Min Act: 0.0000

Data Index: 1764969 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.5988. Min Act: -0.0000

Data Index: 804575 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.6613. Min Act: 0.0000

Data Index: 1004305 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.6125. Min Act: 0.0000

Data Index: 828203 (The Pile)

Max Activating Token Index: 57

Text #5

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.4298. Min Act: -0.0000

Data Index: 766135 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.3357. Min Act: 0.0000

Data Index: 215589 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1919906 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1256402 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.2163. Min Act: -0.0000

Data Index: 812345 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.2685. Min Act: -0.0000

Data Index: 377626 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1489626 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.1291. Min Act: -0.0000

Data Index: 572496 (The Pile)

Max Activating Token Index: 197

Text #13

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.2027. Min Act: -0.0000

Data Index: 173795 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1475850 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.0175. Min Act: -0.0000

Data Index: 1526274 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.0143. Min Act: -0.0000

Data Index: 1688190 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 1.9892. Min Range: -1.9892

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1550327 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1780170 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 1.9892. Min Range: -1.9892

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1803048 (The Pile)

Max Activating Token Index: 699