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

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

Neuron 2395 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: 0.1947. Min Range: -0.1947

Max Act: 0.1947. Min Act: -0.0000

Data Index: 656193 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1919. Min Act: -0.0000

Data Index: 415482 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1196007 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1305. Min Act: -0.0000

Data Index: 714351 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1094. Min Act: 0.0000

Data Index: 878054 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1141019 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1358814 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1097. Min Act: -0.0000

Data Index: 185043 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.1028. Min Act: -0.0000

Data Index: 766271 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0981. Min Act: -0.0000

Data Index: 225763 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1348012 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0974. Min Act: -0.0000

Data Index: 768665 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0919. Min Act: -0.0000

Data Index: 7036 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1106719 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0864. Min Act: -0.0000

Data Index: 922471 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0818. Min Act: -0.0000

Data Index: 351617 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0857. Min Act: -0.0000

Data Index: 408953 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1178266 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0793. Min Act: -0.0000

Data Index: 916981 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.1947. Min Range: -0.1947

Max Act: 0.0779. Min Act: -0.0000

Data Index: 138882 (C4 (Web Text))

Max Activating Token Index: 909