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

Dataset: The Pile

Neuron 3955 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: 1.1797. Min Range: -1.1797

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1745037 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9911. Min Act: -0.0000

Data Index: 261868 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1970378 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1668012 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.6245. Min Act: -0.0000

Data Index: 315683 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.6424. Min Act: -0.0000

Data Index: 449113 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.6323. Min Act: -0.0000

Data Index: 44365 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.5564. Min Act: -0.0000

Data Index: 686416 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1403963 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1931769 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.4788. Min Act: -0.0000

Data Index: 778393 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1762320 (The Pile)

Max Activating Token Index: 1005

Text #12

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1428887 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1992606 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.4887. Min Act: -0.0000

Data Index: 471865 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.4258. Min Act: -0.0000

Data Index: 107507 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1784430 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.4492. Min Act: 0.0000

Data Index: 20358 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1574308 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1249146 (The Pile)

Max Activating Token Index: 742