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

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

Neuron 1766 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0001

Data Index: 854167 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1095. Min Act: -0.0001

Data Index: 458126 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1066. Min Act: -0.0001

Data Index: 715755 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1035. Min Act: -0.0001

Data Index: 519053 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1274652 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0944. Min Act: -0.0001

Data Index: 542296 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0921. Min Act: -0.0001

Data Index: 158452 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0911. Min Act: -0.0001

Data Index: 366553 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1223667 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0892. Min Act: -0.0001

Data Index: 317267 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0924. Min Act: -0.0001

Data Index: 880003 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1326418 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0909. Min Act: -0.0001

Data Index: 72724 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0906. Min Act: -0.0001

Data Index: 662231 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1118323 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0894. Min Act: -0.0001

Data Index: 286976 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0891. Min Act: -0.0001

Data Index: 903879 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0924. Min Act: -0.0001

Data Index: 880008 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0886. Min Act: -0.0001

Data Index: 737375 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1262405 (C4 (Web Text))

Max Activating Token Index: 380