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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1568248 (Python Code)

Max Activating Token Index: 407

Text #1

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1173152 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0961. Min Act: -0.0000

Data Index: 966801 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1576418 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0923. Min Act: -0.0000

Data Index: 946559 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0920. Min Act: -0.0000

Data Index: 643943 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0878. Min Act: -0.0000

Data Index: 96202 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0879. Min Act: -0.0000

Data Index: 339728 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1439155 (Python Code)

Max Activating Token Index: 1014

Text #9

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0846. Min Act: -0.0000

Data Index: 149090 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0813. Min Act: -0.0000

Data Index: 582709 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1513547 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1362462 (Python Code)

Max Activating Token Index: 611

Text #13

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0859. Min Act: -0.0000

Data Index: 605689 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0826. Min Act: -0.0000

Data Index: 255660 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0793. Min Act: -0.0000

Data Index: 247695 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1150841 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0812. Min Act: -0.0000

Data Index: 170290 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0807. Min Act: -0.0000

Data Index: 504440 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0804. Min Act: -0.0000

Data Index: 902649 (C4 (Web Text))

Max Activating Token Index: 622