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

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

Neuron 972 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2491. Min Act: -0.0000

Data Index: 409059 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1136297 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2181. Min Act: -0.0000

Data Index: 906433 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2058. Min Act: -0.0001

Data Index: 790914 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1261891 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1064812 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2068. Min Act: -0.0000

Data Index: 185546 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1982. Min Act: -0.0000

Data Index: 437542 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2011. Min Act: -0.0000

Data Index: 331832 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1121696 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1924. Min Act: -0.0000

Data Index: 656326 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1836. Min Act: -0.0000

Data Index: 354727 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1867. Min Act: -0.0000

Data Index: 722081 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1898. Min Act: -0.0000

Data Index: 568580 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1774. Min Act: -0.0001

Data Index: 92515 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1860. Min Act: -0.0001

Data Index: 375473 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1810. Min Act: -0.0000

Data Index: 194673 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1873. Min Act: -0.0000

Data Index: 351873 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1936. Min Act: -0.0001

Data Index: 20769 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.2491. Min Range: -0.2491

Max Act: 0.1848. Min Act: -0.0001

Data Index: 286002 (C4 (Web Text))

Max Activating Token Index: 232