Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 514 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.4128. Min Act: -0.0000

Data Index: 259240 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.3060. Min Act: -0.0000

Data Index: 418337 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.0493. Min Act: -0.0000

Data Index: 251380 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.2262. Min Act: -0.0000

Data Index: 1668358 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.1560. Min Act: -0.0000

Data Index: 139297 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1565825 (The Pile)

Max Activating Token Index: 908

Text #6

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.0435. Min Act: -0.0000

Data Index: 828543 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1071401 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 1.4128. Min Range: -1.4128

Max Act: 1.0527. Min Act: -0.0000

Data Index: 294315 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1186769 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.9695. Min Act: -0.0000

Data Index: 117566 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1850372 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.9917. Min Act: -0.0000

Data Index: 1774134 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.9071. Min Act: -0.0000

Data Index: 525041 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.9051. Min Act: -0.0000

Data Index: 996893 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.8672. Min Act: -0.0000

Data Index: 892701 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.8482. Min Act: -0.0000

Data Index: 941720 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.8751. Min Act: -0.0000

Data Index: 1252721 (The Pile)

Max Activating Token Index: 438

Text #18

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1355589 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 1.4128. Min Range: -1.4128

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1958646 (The Pile)

Max Activating Token Index: 76