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

Dataset: The Pile

Neuron 2912 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1929916 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0739. Min Act: -0.0000

Data Index: 1372029 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1794239 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1659742 (The Pile)

Max Activating Token Index: 848

Text #4

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0676. Min Act: -0.0000

Data Index: 424752 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0643. Min Act: -0.0000

Data Index: 17280 (The Pile)

Max Activating Token Index: 110

Text #6

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1409395 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0666. Min Act: -0.0000

Data Index: 736491 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1914923 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0607. Min Act: -0.0000

Data Index: 960898 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1761553 (The Pile)

Max Activating Token Index: 591

Text #11

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0700. Min Act: -0.0000

Data Index: 368751 (The Pile)

Max Activating Token Index: 221

Text #12

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1323300 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0666. Min Act: -0.0000

Data Index: 319167 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1750564 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0660. Min Act: -0.0000

Data Index: 113491 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0675. Min Act: -0.0000

Data Index: 358584 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0727. Min Act: -0.0000

Data Index: 423201 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0622. Min Act: -0.0000

Data Index: 675936 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 0.0803. Min Range: -0.0803

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1627166 (The Pile)

Max Activating Token Index: 158