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

Dataset: The Pile

Neuron 782 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: 0.9623. Min Range: -0.9623

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1314338 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1411482 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8708. Min Act: -0.0000

Data Index: 700658 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8064. Min Act: -0.0000

Data Index: 733537 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1226885 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1732660 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6922. Min Act: -0.0000

Data Index: 429737 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6443. Min Act: -0.0000

Data Index: 721880 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.6115. Min Act: -0.0000

Data Index: 332266 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1494625 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1533079 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5161. Min Act: -0.0000

Data Index: 133615 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5072. Min Act: -0.0000

Data Index: 868180 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1498383 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.4959. Min Act: -0.0000

Data Index: 8253 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.4517. Min Act: -0.0000

Data Index: 496718 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1732871 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.4352. Min Act: -0.0000

Data Index: 419382 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1893952 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.4698. Min Act: -0.0000

Data Index: 257308 (The Pile)

Max Activating Token Index: 42