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

Dataset: The Pile

Neuron 647 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: 1.1713. Min Range: -1.1713

Max Act: 1.1713. Min Act: 0.0000

Data Index: 1042596 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7935. Min Act: -0.0000

Data Index: 728414 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1317901 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1325478 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1865108 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1771061 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1957403 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1692052 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1404011 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7164. Min Act: -0.0000

Data Index: 16228 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1844158 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1115046 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1031967 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7233. Min Act: -0.0000

Data Index: 180217 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7164. Min Act: -0.0000

Data Index: 994369 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.6988. Min Act: -0.0000

Data Index: 277863 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1932285 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7383. Min Act: 0.0001

Data Index: 1767145 (The Pile)

Max Activating Token Index: 339

Text #18

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.7020. Min Act: -0.0000

Data Index: 876645 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 1.1713. Min Range: -1.1713

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1818623 (The Pile)

Max Activating Token Index: 821