Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1622 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2244. Min Act: -0.0001

Data Index: 461880 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2118. Min Act: -0.0001

Data Index: 832659 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1121168 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2052. Min Act: -0.0001

Data Index: 741133 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1110965 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2091. Min Act: -0.0001

Data Index: 626203 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.2019. Min Act: -0.0001

Data Index: 943140 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1020748 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1910. Min Act: -0.0001

Data Index: 44568 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1892. Min Act: -0.0001

Data Index: 13692 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1961. Min Act: -0.0001

Data Index: 696292 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1915. Min Act: -0.0001

Data Index: 411784 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1074869 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1866. Min Act: -0.0001

Data Index: 296704 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1860. Min Act: -0.0001

Data Index: 297959 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1844. Min Act: -0.0001

Data Index: 605466 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1892. Min Act: -0.0001

Data Index: 963686 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1836. Min Act: -0.0001

Data Index: 459928 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1310422 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.2244. Min Range: -0.2244

Max Act: 0.1894. Min Act: -0.0001

Data Index: 714444 (C4 (Web Text))

Max Activating Token Index: 65