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

Dataset: The Pile

Neuron 2912 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: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0000

Data Index: 15022 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0753. Min Act: -0.0000

Data Index: 321072 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0677. Min Act: -0.0000

Data Index: 465074 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1854198 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1675613 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1090829 (The Pile)

Max Activating Token Index: 74

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1417632 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0616. Min Act: -0.0000

Data Index: 612204 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0615. Min Act: -0.0000

Data Index: 899065 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0527. Min Act: -0.0000

Data Index: 1726333 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0568. Min Act: -0.0000

Data Index: 853899 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1048071 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0553. Min Act: -0.0000

Data Index: 280908 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0557. Min Act: -0.0000

Data Index: 247518 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0536. Min Act: -0.0000

Data Index: 965694 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1626010 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0509. Min Act: -0.0000

Data Index: 39590 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1313334 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1777641 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0522. Min Act: -0.0000

Data Index: 165049 (The Pile)

Max Activating Token Index: 839