Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 460 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0956. Min Act: -0.0003

Data Index: 1150358 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1012. Min Act: -0.0003

Data Index: 806322 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0929. Min Act: -0.0003

Data Index: 134348 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0931. Min Act: -0.0003

Data Index: 472508 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0930. Min Act: -0.0003

Data Index: 296519 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0893. Min Act: -0.0003

Data Index: 1155785 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0880. Min Act: -0.0003

Data Index: 726373 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0894. Min Act: -0.0003

Data Index: 568881 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0887. Min Act: -0.0004

Data Index: 931113 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0857. Min Act: -0.0004

Data Index: 752003 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0896. Min Act: -0.0003

Data Index: 895615 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0888. Min Act: -0.0003

Data Index: 82302 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1022964 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0859. Min Act: -0.0003

Data Index: 292354 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0856. Min Act: -0.0004

Data Index: 759749 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0867. Min Act: -0.0003

Data Index: 994155 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0831. Min Act: -0.0003

Data Index: 368456 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0825. Min Act: -0.0002

Data Index: 424716 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0792. Min Act: -0.0003

Data Index: 20940 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0810. Min Act: -0.0003

Data Index: 431416 (C4 (Web Text))

Max Activating Token Index: 365