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

Dataset: The Pile

Neuron 2262 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5648. Min Act: -0.0000

Data Index: 257566 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5389. Min Act: -0.0000

Data Index: 956405 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1453253 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1507105 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5230. Min Act: -0.0000

Data Index: 213925 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4836. Min Act: -0.0000

Data Index: 777105 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1580038 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1920519 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1337792 (The Pile)

Max Activating Token Index: 298

Text #9

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4748. Min Act: -0.0000

Data Index: 657206 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4849. Min Act: -0.0000

Data Index: 957673 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1976300 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1034333 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4863. Min Act: -0.0000

Data Index: 131597 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4550. Min Act: 0.0000

Data Index: 611276 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4530. Min Act: -0.0000

Data Index: 91238 (The Pile)

Max Activating Token Index: 977

Text #16

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4681. Min Act: -0.0000

Data Index: 35163 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4613. Min Act: -0.0000

Data Index: 812233 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4582. Min Act: -0.0000

Data Index: 25886 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4601. Min Act: -0.0000

Data Index: 177668 (The Pile)

Max Activating Token Index: 188