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

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

Neuron 1409 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: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0002

Data Index: 843873 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1061. Min Act: -0.0002

Data Index: 807294 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1130. Min Act: -0.0002

Data Index: 916456 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1070. Min Act: -0.0002

Data Index: 78109 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1004. Min Act: -0.0002

Data Index: 928460 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1146478 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0984. Min Act: -0.0002

Data Index: 36715 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1328180 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1022. Min Act: -0.0002

Data Index: 159767 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0976. Min Act: -0.0002

Data Index: 866776 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0967. Min Act: -0.0002

Data Index: 578900 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1152801 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0875. Min Act: -0.0002

Data Index: 133001 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0915. Min Act: -0.0002

Data Index: 470430 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0820. Min Act: -0.0002

Data Index: 464663 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0825. Min Act: -0.0002

Data Index: 966751 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1176641 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0914. Min Act: -0.0002

Data Index: 909726 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1106746 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0830. Min Act: -0.0002

Data Index: 521819 (C4 (Web Text))

Max Activating Token Index: 330