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

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

Neuron 983 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: 0.1052. Min Range: -0.1052

Max Act: 0.1023. Min Act: -0.0002

Data Index: 646101 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0904. Min Act: -0.0002

Data Index: 580443 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1184682 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1147279 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0949. Min Act: -0.0002

Data Index: 209746 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0885. Min Act: -0.0002

Data Index: 598731 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0871. Min Act: -0.0002

Data Index: 903347 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0963. Min Act: -0.0002

Data Index: 506 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1281088 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1015443 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0852. Min Act: -0.0002

Data Index: 313992 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1199764 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0807. Min Act: -0.0002

Data Index: 301075 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0855. Min Act: -0.0002

Data Index: 658476 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1177130 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0824. Min Act: -0.0002

Data Index: 15427 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0789. Min Act: -0.0002

Data Index: 851039 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0908. Min Act: -0.0002

Data Index: 35825 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0848. Min Act: -0.0002

Data Index: 159699 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0792. Min Act: -0.0002

Data Index: 732876 (C4 (Web Text))

Max Activating Token Index: 798