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

Dataset: The Pile

Neuron 1566 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1664. Min Act: -0.0000

Data Index: 910790 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1753096 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1184. Min Act: -0.0000

Data Index: 162084 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1266. Min Act: -0.0000

Data Index: 331090 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1138. Min Act: -0.0000

Data Index: 432448 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1412. Min Act: -0.0000

Data Index: 548208 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1212. Min Act: -0.0000

Data Index: 345084 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1236. Min Act: -0.0000

Data Index: 595423 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1896288 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1138. Min Act: -0.0000

Data Index: 494232 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1456915 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1681808 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1957857 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1250732 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1695212 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1435781 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1048. Min Act: -0.0000

Data Index: 217100 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0964. Min Act: -0.0000

Data Index: 738675 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1521710 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.1664. Min Range: -0.1664

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1745119 (The Pile)

Max Activating Token Index: 1002