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

Dataset: The Pile

Neuron 866 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7675. Min Act: -0.0001

Data Index: 480179 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6654. Min Act: -0.0000

Data Index: 986019 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1645623 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1800762 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1226602 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1236994 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6441. Min Act: -0.0000

Data Index: 10432 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6906. Min Act: -0.0000

Data Index: 766014 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1956373 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6254. Min Act: -0.0000

Data Index: 235920 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6617. Min Act: -0.0000

Data Index: 963717 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1181376 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6528. Min Act: -0.0000

Data Index: 115190 (The Pile)

Max Activating Token Index: 853

Text #13

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1213287 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1220761 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1496533 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6116. Min Act: -0.0000

Data Index: 780019 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6121. Min Act: -0.0000

Data Index: 904603 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5905. Min Act: -0.0000

Data Index: 955018 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1426860 (The Pile)

Max Activating Token Index: 30