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

Dataset: The Pile

Neuron 1450 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1274788 (The Pile)

Max Activating Token Index: 17

Text #1

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1767275 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1963156 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0756. Min Act: -0.0000

Data Index: 566209 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1004. Min Act: -0.0000

Data Index: 518745 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0910. Min Act: -0.0000

Data Index: 531387 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0898. Min Act: -0.0000

Data Index: 261288 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0854. Min Act: -0.0000

Data Index: 570619 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1586557 (The Pile)

Max Activating Token Index: 759

Text #9

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0797. Min Act: -0.0000

Data Index: 70884 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0774. Min Act: -0.0000

Data Index: 133289 (The Pile)

Max Activating Token Index: 385

Text #11

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1585588 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1672738 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1289820 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1914447 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1358398 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0815. Min Act: -0.0000

Data Index: 473175 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1528811 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0710. Min Act: -0.0000

Data Index: 351675 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1640711 (The Pile)

Max Activating Token Index: 853