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

Dataset: The Pile

Neuron 2713 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: 0.7851. Min Range: -0.7851

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1141877 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1999242 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6419. Min Act: -0.0000

Data Index: 729512 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1246226 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1750996 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1340548 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6154. Min Act: -0.0000

Data Index: 609925 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6006. Min Act: -0.0000

Data Index: 195850 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1671945 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1873990 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1984828 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1823012 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1198191 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5534. Min Act: -0.0000

Data Index: 976640 (The Pile)

Max Activating Token Index: 866

Text #14

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1296504 (The Pile)

Max Activating Token Index: 509

Text #15

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5659. Min Act: -0.0000

Data Index: 803941 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1083178 (The Pile)

Max Activating Token Index: 316

Text #17

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5536. Min Act: -0.0000

Data Index: 11271 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1656325 (The Pile)

Max Activating Token Index: 688

Text #19

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5958. Min Act: -0.0000

Data Index: 323849 (The Pile)

Max Activating Token Index: 395