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

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

Neuron 2606 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1155. Min Act: -0.0002

Data Index: 951108 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1015970 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0900. Min Act: -0.0002

Data Index: 344469 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0833. Min Act: -0.0002

Data Index: 661362 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0836. Min Act: -0.0002

Data Index: 399288 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0862. Min Act: -0.0002

Data Index: 128911 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0829. Min Act: -0.0002

Data Index: 592173 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1022430 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0824. Min Act: -0.0002

Data Index: 361804 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1145495 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1201069 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1325171 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0760. Min Act: -0.0002

Data Index: 41404 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0783. Min Act: -0.0002

Data Index: 775326 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0777. Min Act: -0.0002

Data Index: 587900 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0773. Min Act: -0.0002

Data Index: 933406 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0765. Min Act: -0.0002

Data Index: 913899 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0760. Min Act: -0.0002

Data Index: 115774 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0758. Min Act: -0.0002

Data Index: 463484 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0757. Min Act: -0.0002

Data Index: 313929 (C4 (Web Text))

Max Activating Token Index: 163