Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 70 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.9852. Min Act: -0.0000

Data Index: 693372 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.8959. Min Act: -0.0000

Data Index: 233945 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1601690 (The Pile)

Max Activating Token Index: 732

Text #3

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.8275. Min Act: -0.0000

Data Index: 826195 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1764060 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1724218 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7539. Min Act: -0.0000

Data Index: 528564 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1012749 (The Pile)

Max Activating Token Index: 452

Text #8

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1125166 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7545. Min Act: -0.0000

Data Index: 78214 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1479976 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7597. Min Act: -0.0000

Data Index: 166802 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1479787 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6745. Min Act: -0.0000

Data Index: 889264 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1148865 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7140. Min Act: -0.0000

Data Index: 659956 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1386530 (The Pile)

Max Activating Token Index: 42

Text #17

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1177436 (The Pile)

Max Activating Token Index: 605

Text #18

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6991. Min Act: -0.0000

Data Index: 55635 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.9852. Min Range: -0.9852

Max Act: 0.6564. Min Act: -0.0000

Data Index: 204008 (The Pile)

Max Activating Token Index: 607