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

Dataset: The Pile

Neuron 18 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: 1.2910. Min Range: -1.2910

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1183024 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.1647. Min Act: -0.0000

Data Index: 945569 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.2119. Min Act: -0.0000

Data Index: 247636 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.1709. Min Act: -0.0000

Data Index: 1137235 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0884. Min Act: -0.0000

Data Index: 687000 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1804901 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1916537 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1009967 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0364. Min Act: -0.0000

Data Index: 135610 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1840933 (The Pile)

Max Activating Token Index: 272

Text #10

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1563325 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1409242 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1736987 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1263806 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1399252 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0176. Min Act: -0.0000

Data Index: 88646 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0132. Min Act: -0.0000

Data Index: 658180 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0777. Min Act: -0.0000

Data Index: 715413 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 1.2910. Min Range: -1.2910

Max Act: 0.9851. Min Act: -0.0000

Data Index: 299727 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 1.2910. Min Range: -1.2910

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1557426 (The Pile)

Max Activating Token Index: 175