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

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

Neuron 416 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: 0.1023. Min Range: -0.1023

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1277801 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1185126 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0002

Data Index: 202205 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0949. Min Act: -0.0002

Data Index: 546774 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0928. Min Act: -0.0002

Data Index: 647281 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1107281 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1231921 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0921. Min Act: -0.0002

Data Index: 605783 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1256098 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0914. Min Act: -0.0002

Data Index: 726588 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0907. Min Act: -0.0002

Data Index: 360546 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0904. Min Act: -0.0002

Data Index: 153632 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1001399 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0893. Min Act: -0.0002

Data Index: 195141 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0908. Min Act: -0.0002

Data Index: 356544 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0901. Min Act: -0.0002

Data Index: 904564 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1543851 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1043258 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0884. Min Act: -0.0002

Data Index: 174482 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0883. Min Act: -0.0002

Data Index: 662804 (C4 (Web Text))

Max Activating Token Index: 354