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

Dataset: The Pile

Neuron 1106 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.6783. Min Act: -0.0000

Data Index: 854331 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1624055 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5040. Min Act: -0.0000

Data Index: 77932 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1478480 (The Pile)

Max Activating Token Index: 787

Text #4

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5115. Min Act: -0.0000

Data Index: 266236 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1130597 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5487. Min Act: -0.0000

Data Index: 766738 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5117. Min Act: -0.0000

Data Index: 195796 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1971506 (The Pile)

Max Activating Token Index: 231

Text #9

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1432875 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1882621 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1344464 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4747. Min Act: -0.0000

Data Index: 586849 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1488957 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4891. Min Act: -0.0000

Data Index: 300359 (The Pile)

Max Activating Token Index: 939

Text #15

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1337650 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4580. Min Act: -0.0000

Data Index: 734104 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1982629 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1928344 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.6783. Min Range: -0.6783

Max Act: 0.4346. Min Act: -0.0000

Data Index: 133985 (The Pile)

Max Activating Token Index: 172