Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 946 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1049334 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1356916 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0947. Min Act: -0.0002

Data Index: 593017 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0989. Min Act: -0.0002

Data Index: 849409 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0945. Min Act: -0.0002

Data Index: 180061 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0909. Min Act: -0.0002

Data Index: 31362 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0857. Min Act: -0.0002

Data Index: 6919 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0837. Min Act: -0.0002

Data Index: 405055 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1254673 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0832. Min Act: -0.0002

Data Index: 385120 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1304146 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1042426 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0791. Min Act: -0.0002

Data Index: 492891 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0816. Min Act: -0.0002

Data Index: 833437 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0701. Min Act: -0.0002

Data Index: 275446 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1351719 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0713. Min Act: -0.0002

Data Index: 990872 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0892. Min Act: -0.0002

Data Index: 587446 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1111044 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.1087. Min Range: -0.1087

Max Act: 0.0792. Min Act: -0.0002

Data Index: 184560 (C4 (Web Text))

Max Activating Token Index: 461