Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 189 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.1039. Min Act: -0.0002

Data Index: 425094 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0927. Min Act: -0.0002

Data Index: 159761 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0931. Min Act: -0.0002

Data Index: 915029 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1244767 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0917. Min Act: -0.0002

Data Index: 887091 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0877. Min Act: -0.0002

Data Index: 766795 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0873. Min Act: -0.0002

Data Index: 506675 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0874. Min Act: -0.0002

Data Index: 58098 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0846. Min Act: -0.0002

Data Index: 497467 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0803. Min Act: -0.0002

Data Index: 310776 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1338129 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0767. Min Act: -0.0002

Data Index: 55909 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0812. Min Act: -0.0002

Data Index: 975976 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0748. Min Act: -0.0002

Data Index: 756237 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0797. Min Act: -0.0002

Data Index: 722379 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0818. Min Act: -0.0002

Data Index: 834858 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0711. Min Act: -0.0002

Data Index: 750970 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0748. Min Act: -0.0002

Data Index: 444368 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0786. Min Act: -0.0002

Data Index: 60828 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1324130 (C4 (Web Text))

Max Activating Token Index: 83