Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2045 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.5911. Min Act: -0.0000

Data Index: 759140 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1838369 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.3220. Min Act: -0.0000

Data Index: 809395 (The Pile)

Max Activating Token Index: 833

Text #3

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.3881. Min Act: -0.0000

Data Index: 235643 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.2165. Min Act: -0.0000

Data Index: 419231 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.3539. Min Act: -0.0000

Data Index: 638324 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1128173 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.2772. Min Act: -0.0000

Data Index: 1851650 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1540343 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.2118. Min Act: -0.0000

Data Index: 1317540 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1300. Min Act: -0.0000

Data Index: 610505 (The Pile)

Max Activating Token Index: 30

Text #11

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1918288 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1814196 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1432928 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1583. Min Act: -0.0000

Data Index: 757955 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1736. Min Act: -0.0000

Data Index: 279524 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0977. Min Act: -0.0000

Data Index: 555293 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0671. Min Act: -0.0000

Data Index: 49798 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1940491 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1716518 (The Pile)

Max Activating Token Index: 680