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

Dataset: The Pile

Neuron 1788 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: 0.4506. Min Range: -0.4506

Max Act: 0.4487. Min Act: -0.0000

Data Index: 552364 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.4506. Min Act: -0.0000

Data Index: 160405 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1167479 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1359896 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1515041 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1605969 (The Pile)

Max Activating Token Index: 499

Text #6

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3466. Min Act: -0.0000

Data Index: 745365 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1852077 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1893894 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1535468 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1672304 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3782. Min Act: -0.0000

Data Index: 628150 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3397. Min Act: -0.0000

Data Index: 321707 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3714. Min Act: -0.0000

Data Index: 790884 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1514090 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1627647 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3073. Min Act: -0.0000

Data Index: 576217 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3047. Min Act: -0.0000

Data Index: 839681 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1500961 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.4506. Min Range: -0.4506

Max Act: 0.2741. Min Act: -0.0000

Data Index: 689734 (The Pile)

Max Activating Token Index: 166