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

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

Neuron 3615 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: 0.1281. Min Range: -0.1281

Max Act: 0.1281. Min Act: -0.0002

Data Index: 784370 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1205826 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1068. Min Act: -0.0002

Data Index: 734841 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1032. Min Act: -0.0002

Data Index: 130800 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0982. Min Act: -0.0002

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1022. Min Act: -0.0002

Data Index: 231916 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0880. Min Act: -0.0002

Data Index: 52185 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1208750 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0890. Min Act: -0.0002

Data Index: 236897 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0855. Min Act: -0.0002

Data Index: 383396 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0895. Min Act: -0.0002

Data Index: 884200 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0898. Min Act: -0.0002

Data Index: 507812 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0815. Min Act: -0.0002

Data Index: 720203 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0873. Min Act: -0.0002

Data Index: 240501 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0909. Min Act: -0.0002

Data Index: 656445 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1291991 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1128745 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1104370 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0872. Min Act: -0.0002

Data Index: 73518 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1315211 (C4 (Web Text))

Max Activating Token Index: 961