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

Dataset: The Pile

Neuron 3589 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.7688. Min Act: -0.0000

Data Index: 130807 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.7145. Min Act: -0.0000

Data Index: 549050 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1164614 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.4425. Min Act: -0.0000

Data Index: 530087 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3881. Min Act: -0.0000

Data Index: 331028 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3760. Min Act: -0.0000

Data Index: 453183 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1893620 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.2837. Min Act: -0.0000

Data Index: 1126567 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1079919 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.2640. Min Act: -0.0000

Data Index: 67324 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1243994 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.2523. Min Act: -0.0000

Data Index: 227087 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.2375. Min Act: -0.0000

Data Index: 536102 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.1545. Min Act: -0.0000

Data Index: 543855 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.1960. Min Act: -0.0000

Data Index: 51308 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.1888. Min Act: -0.0000

Data Index: 919766 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.1618. Min Act: -0.0000

Data Index: 821336 (The Pile)

Max Activating Token Index: 335

Text #17

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.0797. Min Act: -0.0000

Data Index: 135421 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1035351 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.1302. Min Act: 0.0000

Data Index: 935990 (The Pile)

Max Activating Token Index: 481