Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1425 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.1030. Min Act: -0.0001

Data Index: 651426 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0941. Min Act: -0.0001

Data Index: 26347 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0811. Min Act: -0.0001

Data Index: 609359 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1027231 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1240693 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0820. Min Act: -0.0001

Data Index: 653686 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0847. Min Act: -0.0001

Data Index: 7186 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0911. Min Act: -0.0001

Data Index: 359604 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0849. Min Act: -0.0001

Data Index: 786670 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0836. Min Act: -0.0001

Data Index: 787740 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0818. Min Act: -0.0001

Data Index: 966903 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0777. Min Act: -0.0001

Data Index: 310229 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1305317 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0837. Min Act: -0.0001

Data Index: 625768 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0776. Min Act: -0.0001

Data Index: 12774 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0770. Min Act: -0.0001

Data Index: 455289 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0769. Min Act: -0.0001

Data Index: 422511 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1072045 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1047890 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0730. Min Act: -0.0001

Data Index: 928359 (C4 (Web Text))

Max Activating Token Index: 646