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

Dataset: The Pile

Neuron 911 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: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0000

Data Index: 457071 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0738. Min Act: -0.0000

Data Index: 477742 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0672. Min Act: -0.0000

Data Index: 543991 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1537432 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1322000 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0617. Min Act: -0.0000

Data Index: 65442 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0594. Min Act: -0.0000

Data Index: 438552 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0632. Min Act: -0.0000

Data Index: 594665 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1991707 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1314292 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0579. Min Act: -0.0000

Data Index: 28396 (The Pile)

Max Activating Token Index: 598

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0574. Min Act: -0.0000

Data Index: 1584221 (The Pile)

Max Activating Token Index: 873

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1197733 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1417799 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0539. Min Act: -0.0000

Data Index: 1513635 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0553. Min Act: -0.0000

Data Index: 553894 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1015244 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1175199 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0541. Min Act: -0.0000

Data Index: 77798 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0571. Min Act: -0.0000

Data Index: 949546 (The Pile)

Max Activating Token Index: 288