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

Dataset: The Pile

Neuron 1470 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7745. Min Act: 0.0000

Data Index: 579837 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6710. Min Act: -0.0000

Data Index: 894623 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7044. Min Act: -0.0000

Data Index: 771895 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1715433 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6089. Min Act: -0.0000

Data Index: 180603 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1977932 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6220. Min Act: -0.0000

Data Index: 563723 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6108. Min Act: -0.0000

Data Index: 263856 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1523223 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5687. Min Act: -0.0000

Data Index: 38969 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1781265 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6137. Min Act: -0.0000

Data Index: 13846 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5545. Min Act: -0.0000

Data Index: 38724 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5424. Min Act: -0.0000

Data Index: 815403 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1265255 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5647. Min Act: -0.0000

Data Index: 928161 (The Pile)

Max Activating Token Index: 40

Text #16

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6048. Min Act: 0.0000

Data Index: 1039484 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1229048 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1509258 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5713. Min Act: -0.0000

Data Index: 348460 (The Pile)

Max Activating Token Index: 694