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

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

Neuron 5045 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1482811 (Python Code)

Max Activating Token Index: 389

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1329384 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1145445 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1276401 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0868. Min Act: -0.0001

Data Index: 642881 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0887. Min Act: -0.0001

Data Index: 567184 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0909. Min Act: -0.0001

Data Index: 220723 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0826. Min Act: -0.0001

Data Index: 503940 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0793. Min Act: -0.0001

Data Index: 125980 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0785. Min Act: -0.0001

Data Index: 260858 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0783. Min Act: -0.0001

Data Index: 851994 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0800. Min Act: -0.0001

Data Index: 31895 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0892. Min Act: -0.0001

Data Index: 610936 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0815. Min Act: -0.0001

Data Index: 838558 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0756. Min Act: -0.0001

Data Index: 961223 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0753. Min Act: -0.0001

Data Index: 470583 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0761. Min Act: -0.0001

Data Index: 733853 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1182210 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0744. Min Act: -0.0001

Data Index: 562290 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0769. Min Act: -0.0001

Data Index: 500550 (C4 (Web Text))

Max Activating Token Index: 14