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

Dataset: The Pile

Neuron 1198 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: 1.2182. Min Range: -1.2182

Max Act: 1.1352. Min Act: -0.0000

Data Index: 46755 (The Pile)

Max Activating Token Index: 724

Text #1

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1572615 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1549604 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1336021 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.1568. Min Act: -0.0000

Data Index: 756480 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1218752 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.1220. Min Act: -0.0000

Data Index: 560424 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0666. Min Act: -0.0000

Data Index: 54777 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0724. Min Act: -0.0000

Data Index: 201350 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.1743. Min Act: -0.0000

Data Index: 1368716 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.1456. Min Act: -0.0000

Data Index: 326441 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.1007. Min Act: -0.0000

Data Index: 370400 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0251. Min Act: -0.0000

Data Index: 296806 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1723228 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.1435. Min Act: -0.0000

Data Index: 779973 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0155. Min Act: -0.0000

Data Index: 127521 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1033067 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0487. Min Act: -0.0000

Data Index: 84706 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0734. Min Act: -0.0000

Data Index: 116616 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0584. Min Act: -0.0000

Data Index: 927273 (The Pile)

Max Activating Token Index: 473