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

Dataset: The Pile

Neuron 2253 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: 0.4726. Min Range: -0.4726

Max Act: 0.4726. Min Act: -0.0000

Data Index: 325888 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1952971 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1560812 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4045. Min Act: -0.0000

Data Index: 995825 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1656817 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1473631 (The Pile)

Max Activating Token Index: 975

Text #6

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3877. Min Act: -0.0000

Data Index: 198475 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1880781 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1202655 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3624. Min Act: -0.0000

Data Index: 302061 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1345125 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1969492 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1078921 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3681. Min Act: -0.0000

Data Index: 34714 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3579. Min Act: -0.0000

Data Index: 721 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3541. Min Act: -0.0000

Data Index: 836339 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3749. Min Act: -0.0000

Data Index: 975486 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3425. Min Act: -0.0000

Data Index: 556231 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1972743 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3501. Min Act: -0.0000

Data Index: 19865 (The Pile)

Max Activating Token Index: 278