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

Dataset: The Pile

Neuron 2731 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1804217 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.7534. Min Act: -0.0000

Data Index: 198222 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1075491 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1106888 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.7522. Min Act: -0.0000

Data Index: 768358 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6702. Min Act: -0.0000

Data Index: 906639 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6928. Min Act: -0.0000

Data Index: 115428 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1331357 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1405311 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1837947 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6619. Min Act: -0.0000

Data Index: 402277 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1514601 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6144. Min Act: -0.0000

Data Index: 931420 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6515. Min Act: -0.0000

Data Index: 500178 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6056. Min Act: -0.0000

Data Index: 260880 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6972. Min Act: -0.0000

Data Index: 899707 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1268746 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1231759 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1430482 (The Pile)

Max Activating Token Index: 549

Text #19

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1285484 (The Pile)

Max Activating Token Index: 978