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

Dataset: The Pile

Neuron 4333 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: 1.6615. Min Range: -1.6615

Max Act: 1.5268. Min Act: -0.0000

Data Index: 883008 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.6615. Min Act: -0.0000

Data Index: 1110508 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.5340. Min Act: -0.0000

Data Index: 83740 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.4737. Min Act: -0.0000

Data Index: 364936 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.3295. Min Act: -0.0000

Data Index: 713202 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.3269. Min Act: -0.0000

Data Index: 891369 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1289593 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.3717. Min Act: -0.0000

Data Index: 1973829 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.3047. Min Act: -0.0000

Data Index: 1527264 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.3345. Min Act: -0.0000

Data Index: 1586671 (The Pile)

Max Activating Token Index: 401

Text #10

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.3593. Min Act: -0.0000

Data Index: 210970 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1901861 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1311017 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1969694 (The Pile)

Max Activating Token Index: 192

Text #14

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1531704 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.2246. Min Act: -0.0000

Data Index: 678316 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.1870. Min Act: -0.0000

Data Index: 7914 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.3134. Min Act: -0.0000

Data Index: 1290338 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.2087. Min Act: -0.0000

Data Index: 868498 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 1.6615. Min Range: -1.6615

Max Act: 1.2769. Min Act: -0.0000

Data Index: 1659445 (The Pile)

Max Activating Token Index: 382