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

Dataset: The Pile

Neuron 930 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.4875. Min Act: -0.0000

Data Index: 92994 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.4460. Min Act: -0.0000

Data Index: 750173 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1917119 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1776753 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.0362. Min Act: -0.0000

Data Index: 575282 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.0748. Min Act: -0.0000

Data Index: 301508 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1300985 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1793507 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.0616. Min Act: -0.0000

Data Index: 1462152 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.9510. Min Act: -0.0000

Data Index: 76061 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1613694 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.9420. Min Act: -0.0000

Data Index: 574090 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.8017. Min Act: -0.0000

Data Index: 562535 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.9215. Min Act: -0.0000

Data Index: 787530 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.9593. Min Act: -0.0000

Data Index: 363800 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 1.4875. Min Range: -1.4875

Max Act: 1.0247. Min Act: -0.0000

Data Index: 539409 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.9468. Min Act: -0.0000

Data Index: 594239 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1850457 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.9567. Min Act: -0.0000

Data Index: 861807 (The Pile)

Max Activating Token Index: 116

Text #19

Max Range: 1.4875. Min Range: -1.4875

Max Act: 0.9056. Min Act: -0.0000

Data Index: 547547 (The Pile)

Max Activating Token Index: 54