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

Dataset: The Pile

Neuron 4809 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.8097. Min Act: 0.0000

Data Index: 596737 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 3.0012. Min Range: -3.0012

Max Act: 3.0012. Min Act: -0.0000

Data Index: 926781 (The Pile)

Max Activating Token Index: 270

Text #2

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.2937. Min Act: -0.0000

Data Index: 124104 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0130. Min Act: -0.0000

Data Index: 585757 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 3.0012. Min Range: -3.0012

Max Act: 1.9998. Min Act: -0.0000

Data Index: 317325 (The Pile)

Max Activating Token Index: 975

Text #5

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.1191. Min Act: -0.0000

Data Index: 160572 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0856. Min Act: -0.0000

Data Index: 212072 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0935. Min Act: -0.0000

Data Index: 1977616 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0878. Min Act: -0.0000

Data Index: 291255 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0661. Min Act: -0.0000

Data Index: 491325 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 3.0012. Min Range: -3.0012

Max Act: 1.9602. Min Act: -0.0000

Data Index: 169472 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 3.0012. Min Range: -3.0012

Max Act: 1.9580. Min Act: -0.0000

Data Index: 1218679 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0614. Min Act: -0.0000

Data Index: 1267609 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0284. Min Act: -0.0000

Data Index: 1587859 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0512. Min Act: -0.0000

Data Index: 1725578 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0088. Min Act: -0.0000

Data Index: 266333 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 3.0012. Min Range: -3.0012

Max Act: 2.0276. Min Act: -0.0000

Data Index: 1397960 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 3.0012. Min Range: -3.0012

Max Act: 1.8708. Min Act: -0.0000

Data Index: 1232194 (The Pile)

Max Activating Token Index: 817

Text #18

Max Range: 3.0012. Min Range: -3.0012

Max Act: 1.9792. Min Act: -0.0000

Data Index: 699078 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 3.0012. Min Range: -3.0012

Max Act: 1.8529. Min Act: -0.0000

Data Index: 1836715 (The Pile)

Max Activating Token Index: 949