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

Dataset: The Pile

Neuron 362 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1623500 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.7067. Min Act: -0.0000

Data Index: 605211 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6539. Min Act: -0.0000

Data Index: 455169 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1907574 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5609. Min Act: -0.0000

Data Index: 981399 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5760. Min Act: -0.0000

Data Index: 984481 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5790. Min Act: -0.0000

Data Index: 846233 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1773800 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1704812 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1964650 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1673228 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1817566 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1591021 (The Pile)

Max Activating Token Index: 187

Text #13

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1629381 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4808. Min Act: -0.0000

Data Index: 884636 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4625. Min Act: -0.0000

Data Index: 198941 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1968082 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4595. Min Act: -0.0000

Data Index: 707427 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4301. Min Act: -0.0000

Data Index: 99547 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4693. Min Act: -0.0000

Data Index: 501818 (The Pile)

Max Activating Token Index: 26