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

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

Neuron 1252 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2901. Min Act: -0.0000

Data Index: 818637 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1200641 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2754. Min Act: -0.0000

Data Index: 653496 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1138119 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2180. Min Act: -0.0000

Data Index: 405805 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1011020 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2155. Min Act: -0.0000

Data Index: 710231 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1980. Min Act: -0.0000

Data Index: 741162 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.2039. Min Act: -0.0000

Data Index: 889488 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1951. Min Act: -0.0000

Data Index: 48241 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1946. Min Act: -0.0000

Data Index: 769927 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1811. Min Act: -0.0000

Data Index: 969441 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1855. Min Act: -0.0000

Data Index: 141607 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1847. Min Act: -0.0000

Data Index: 842990 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1866. Min Act: -0.0000

Data Index: 91006 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1858. Min Act: -0.0000

Data Index: 777095 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1231642 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1897. Min Act: -0.0000

Data Index: 419263 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1023413 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.2901. Min Range: -0.2901

Max Act: 0.1679. Min Act: -0.0000

Data Index: 269109 (C4 (Web Text))

Max Activating Token Index: 433