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

Dataset: The Pile

Neuron 3921 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: 0.0960. Min Range: -0.0960

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1750247 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0773. Min Act: -0.0000

Data Index: 86008 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1677212 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0666. Min Act: -0.0000

Data Index: 269963 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0745. Min Act: -0.0000

Data Index: 760268 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0715. Min Act: -0.0000

Data Index: 732481 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1609489 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0737. Min Act: -0.0000

Data Index: 570341 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0700. Min Act: -0.0000

Data Index: 548402 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1454467 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1194556 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1729243 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0669. Min Act: -0.0000

Data Index: 479229 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1040068 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1653370 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1780632 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1929469 (The Pile)

Max Activating Token Index: 699

Text #17

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1414937 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0681. Min Act: -0.0000

Data Index: 905200 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 0.0960. Min Range: -0.0960

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1575123 (The Pile)

Max Activating Token Index: 795