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

Dataset: The Pile

Neuron 3435 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.3848. Min Act: -0.0000

Data Index: 1349943 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2874. Min Act: -0.0000

Data Index: 898651 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1123675 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1432731 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1368946 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1609767 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2431. Min Act: -0.0000

Data Index: 608879 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1156913 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1466037 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1538360 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1954150 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2245. Min Act: -0.0000

Data Index: 251822 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2271. Min Act: -0.0000

Data Index: 660381 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1495948 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2043. Min Act: -0.0000

Data Index: 854629 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.1887. Min Act: -0.0000

Data Index: 313151 (The Pile)

Max Activating Token Index: 473

Text #16

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2275. Min Act: -0.0000

Data Index: 601573 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1963069 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.1891. Min Act: -0.0000

Data Index: 270891 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 0.3848. Min Range: -0.3848

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1435287 (The Pile)

Max Activating Token Index: 890