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

Dataset: The Pile

Neuron 3769 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1407091 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1802158 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1152953 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.8281. Min Act: -0.0000

Data Index: 665293 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7698. Min Act: -0.0000

Data Index: 164622 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1243769 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1861765 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7446. Min Act: -0.0000

Data Index: 503596 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1693820 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1294370 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1639866 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6140. Min Act: -0.0000

Data Index: 714073 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5675. Min Act: -0.0000

Data Index: 263020 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.6187. Min Act: -0.0000

Data Index: 735649 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1957295 (The Pile)

Max Activating Token Index: 520

Text #15

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1866407 (The Pile)

Max Activating Token Index: 732

Text #16

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.7175. Min Act: -0.0000

Data Index: 309508 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1494568 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1507978 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 0.8873. Min Range: -0.8873

Max Act: 0.5433. Min Act: -0.0000

Data Index: 186718 (The Pile)

Max Activating Token Index: 864