Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 825 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1022781 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0876. Min Act: -0.0002

Data Index: 126579 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0897. Min Act: -0.0002

Data Index: 683471 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1202608 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0002

Data Index: 167871 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0896. Min Act: -0.0002

Data Index: 61722 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0885. Min Act: -0.0002

Data Index: 244165 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0877. Min Act: -0.0002

Data Index: 565295 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1111819 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0875. Min Act: -0.0002

Data Index: 191331 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1212958 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0873. Min Act: -0.0002

Data Index: 523395 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0853. Min Act: -0.0002

Data Index: 186585 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0875. Min Act: -0.0002

Data Index: 329937 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0844. Min Act: -0.0002

Data Index: 680412 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0840. Min Act: -0.0002

Data Index: 834619 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0867. Min Act: -0.0002

Data Index: 956789 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0833. Min Act: -0.0002

Data Index: 432508 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0856. Min Act: -0.0002

Data Index: 900514 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0857. Min Act: -0.0002

Data Index: 256737 (C4 (Web Text))

Max Activating Token Index: 839