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

Dataset: The Pile

Neuron 1316 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1234. Min Act: 0.0000

Data Index: 1339543 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1204. Min Act: -0.0000

Data Index: 218566 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1808523 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1080. Min Act: 0.0000

Data Index: 1290296 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1059. Min Act: 0.0000

Data Index: 92970 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1080. Min Act: 0.0000

Data Index: 1075523 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1044. Min Act: 0.0000

Data Index: 1857987 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1033. Min Act: 0.0000

Data Index: 170012 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1028. Min Act: 0.0000

Data Index: 400868 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1022. Min Act: 0.0000

Data Index: 907088 (The Pile)

Max Activating Token Index: 29

Text #10

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1017. Min Act: 0.0000

Data Index: 1310416 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1005. Min Act: 0.0000

Data Index: 1933415 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0991. Min Act: 0.0000

Data Index: 1705430 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1179568 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0982. Min Act: 0.0000

Data Index: 137099 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0972. Min Act: 0.0000

Data Index: 339261 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0961. Min Act: 0.0000

Data Index: 1506716 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0951. Min Act: 0.0000

Data Index: 1624683 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0951. Min Act: 0.0000

Data Index: 1040826 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0949. Min Act: 0.0000

Data Index: 719315 (The Pile)

Max Activating Token Index: 456