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

Dataset: The Pile

Neuron 3251 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: 3.8650. Min Range: -3.8650

Max Act: 3.8263. Min Act: -0.0000

Data Index: 1136080 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.4906. Min Act: -0.0000

Data Index: 1749999 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.4507. Min Act: -0.0000

Data Index: 619199 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.8650. Min Act: -0.0000

Data Index: 1381272 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.6690. Min Act: -0.0000

Data Index: 93724 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.5597. Min Act: -0.0000

Data Index: 157263 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.4070. Min Act: -0.0000

Data Index: 1183817 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.4699. Min Act: -0.0000

Data Index: 1686491 (The Pile)

Max Activating Token Index: 843

Text #8

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.2962. Min Act: -0.0000

Data Index: 5043 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.0706. Min Act: -0.0000

Data Index: 1588127 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 3.8650. Min Range: -3.8650

Max Act: 2.4649. Min Act: -0.0000

Data Index: 1910963 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.1066. Min Act: -0.0000

Data Index: 1589384 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.0633. Min Act: -0.0000

Data Index: 1974251 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 3.8650. Min Range: -3.8650

Max Act: 2.9445. Min Act: -0.0000

Data Index: 1282310 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.0669. Min Act: -0.0000

Data Index: 1934107 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.0202. Min Act: -0.0000

Data Index: 946257 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 3.8650. Min Range: -3.8650

Max Act: 2.9965. Min Act: -0.0000

Data Index: 8507 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.0044. Min Act: -0.0000

Data Index: 1779960 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 3.8650. Min Range: -3.8650

Max Act: 2.8675. Min Act: -0.0000

Data Index: 1708899 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 3.8650. Min Range: -3.8650

Max Act: 3.0028. Min Act: -0.0000

Data Index: 1868708 (The Pile)

Max Activating Token Index: 546