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

Dataset: The Pile

Neuron 3643 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: 3.7870. Min Range: -3.7870

Max Act: 3.7870. Min Act: -0.0000

Data Index: 813836 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 3.7870. Min Range: -3.7870

Max Act: 3.6604. Min Act: -0.0000

Data Index: 1261317 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 3.7870. Min Range: -3.7870

Max Act: 3.7497. Min Act: -0.0000

Data Index: 1686390 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 3.7870. Min Range: -3.7870

Max Act: 3.6813. Min Act: -0.0000

Data Index: 1491824 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 3.7870. Min Range: -3.7870

Max Act: 3.2076. Min Act: -0.0000

Data Index: 991867 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.9701. Min Act: -0.0000

Data Index: 1632177 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 3.7870. Min Range: -3.7870

Max Act: 3.5462. Min Act: -0.0000

Data Index: 1482821 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 3.7870. Min Range: -3.7870

Max Act: 3.0492. Min Act: -0.0000

Data Index: 21034 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.8851. Min Act: -0.0000

Data Index: 1908414 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.7195. Min Act: -0.0000

Data Index: 309725 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 3.7870. Min Range: -3.7870

Max Act: 3.2633. Min Act: -0.0000

Data Index: 484227 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.8877. Min Act: -0.0000

Data Index: 1445442 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.7741. Min Act: -0.0000

Data Index: 904287 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.7781. Min Act: -0.0000

Data Index: 702362 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.9117. Min Act: -0.0000

Data Index: 190710 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.8883. Min Act: -0.0000

Data Index: 1981106 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.7241. Min Act: -0.0000

Data Index: 1214977 (The Pile)

Max Activating Token Index: 11

Text #17

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.5583. Min Act: -0.0000

Data Index: 1586467 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.6843. Min Act: -0.0000

Data Index: 1243565 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 3.7870. Min Range: -3.7870

Max Act: 2.5211. Min Act: -0.0000

Data Index: 999427 (The Pile)

Max Activating Token Index: 914