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

Dataset: The Pile

Neuron 525 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9561. Min Act: -0.0000

Data Index: 510305 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8566. Min Act: -0.0000

Data Index: 484166 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1814421 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1229067 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8106. Min Act: -0.0000

Data Index: 221227 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1124486 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1425480 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1490849 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7383. Min Act: -0.0001

Data Index: 1913367 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.6759. Min Act: -0.0000

Data Index: 832067 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1187234 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8282. Min Act: -0.0000

Data Index: 492280 (The Pile)

Max Activating Token Index: 932

Text #12

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.6590. Min Act: -0.0000

Data Index: 757786 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1933029 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1321349 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1676067 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1603239 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1632437 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.6314. Min Act: -0.0000

Data Index: 830661 (The Pile)

Max Activating Token Index: 706

Text #19

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1176068 (The Pile)

Max Activating Token Index: 311