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

Dataset: The Pile

Neuron 384 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 46028 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0000

Data Index: 709206 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1547125 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1015568 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 296867 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 230144 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 930717 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 104734 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 12062 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1476779 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 910509 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 915381 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 365933 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1187337 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1872899 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1601601 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1106601 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1688431 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 786244 (The Pile)

Max Activating Token Index: 891

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1569542 (The Pile)

Max Activating Token Index: 757