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

Dataset: The Pile

Neuron 3727 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1059119 (The Pile)

Max Activating Token Index: 217

Text #1

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.2661. Min Act: -0.0000

Data Index: 1302333 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1259134 (The Pile)

Max Activating Token Index: 562

Text #3

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1280206 (The Pile)

Max Activating Token Index: 851

Text #4

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1394941 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0625. Min Act: -0.0000

Data Index: 701544 (The Pile)

Max Activating Token Index: 986

Text #6

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1240043 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9349. Min Act: -0.0000

Data Index: 39779 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9928. Min Act: 0.0000

Data Index: 1604473 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1518901 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1205181 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9561. Min Act: 0.0000

Data Index: 1874179 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8043. Min Act: -0.0000

Data Index: 599743 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.7195. Min Act: -0.0000

Data Index: 967283 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1771909 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 1.3010. Min Range: -1.3010

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1106980 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1855264 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1313872 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.8683. Min Act: -0.0000

Data Index: 595002 (The Pile)

Max Activating Token Index: 403

Text #19

Max Range: 1.3010. Min Range: -1.3010

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1767964 (The Pile)

Max Activating Token Index: 835