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

Dataset: The Pile

Neuron 697 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: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: -0.0000

Data Index: 319816 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1222. Min Act: -0.0000

Data Index: 657790 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1224. Min Act: -0.0000

Data Index: 591957 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1160. Min Act: -0.0000

Data Index: 723467 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1070. Min Act: -0.0000

Data Index: 827688 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1490180 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1550557 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1239789 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1106. Min Act: -0.0000

Data Index: 719878 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1076. Min Act: -0.0000

Data Index: 317732 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1755049 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0977. Min Act: -0.0000

Data Index: 201414 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1626547 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1009. Min Act: -0.0000

Data Index: 173792 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1856325 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1067. Min Act: -0.0000

Data Index: 505499 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1683194 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1004. Min Act: -0.0000

Data Index: 613389 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.0964. Min Act: -0.0000

Data Index: 310371 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1005223 (The Pile)

Max Activating Token Index: 991