Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4759 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.2833. Min Act: -0.0002

Data Index: 1529385 (Python Code)

Max Activating Token Index: 889

Text #1

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.1303. Min Act: -0.0002

Data Index: 1322862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.1274. Min Act: -0.0002

Data Index: 669640 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.1212. Min Act: -0.0002

Data Index: 1233715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0914. Min Act: -0.0002

Data Index: 124905 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0893. Min Act: -0.0002

Data Index: 607280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0809. Min Act: -0.0002

Data Index: 732565 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1199996 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0787. Min Act: -0.0002

Data Index: 135974 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0813. Min Act: -0.0002

Data Index: 741234 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1591930 (Python Code)

Max Activating Token Index: 896

Text #11

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0708. Min Act: -0.0002

Data Index: 957642 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1121134 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0704. Min Act: -0.0002

Data Index: 950698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1139484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1560512 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0608. Min Act: -0.0002

Data Index: 940843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0614. Min Act: -0.0002

Data Index: 555893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1428222 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 0.2833. Min Range: -0.2833

Max Act: 0.0563. Min Act: -0.0002

Data Index: 474393 (C4 (Web Text))

Max Activating Token Index: 1023