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

Dataset: The Pile

Neuron 302 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.8320. Min Act: -0.0000

Data Index: 339258 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6354. Min Act: -0.0000

Data Index: 1552451 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5681. Min Act: -0.0000

Data Index: 1859728 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6688. Min Act: -0.0000

Data Index: 962436 (The Pile)

Max Activating Token Index: 403

Text #4

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6808. Min Act: -0.0000

Data Index: 1480269 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.6330. Min Act: -0.0000

Data Index: 677684 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.4689. Min Act: -0.0000

Data Index: 1264791 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5657. Min Act: -0.0000

Data Index: 724632 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5062. Min Act: -0.0000

Data Index: 793798 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5985. Min Act: -0.0000

Data Index: 953864 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5777. Min Act: -0.0000

Data Index: 1651542 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.5692. Min Act: -0.0000

Data Index: 404453 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.3108. Min Act: -0.0000

Data Index: 1393655 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.3019. Min Act: -0.0000

Data Index: 1281258 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.3974. Min Act: -0.0000

Data Index: 1103867 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.3354. Min Act: -0.0000

Data Index: 713117 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.2969. Min Act: -0.0000

Data Index: 84216 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.1858. Min Act: -0.0000

Data Index: 640388 (The Pile)

Max Activating Token Index: 584

Text #18

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.2755. Min Act: -0.0000

Data Index: 595741 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 2.8320. Min Range: -2.8320

Max Act: 2.1527. Min Act: -0.0000

Data Index: 364766 (The Pile)

Max Activating Token Index: 845