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

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

Neuron 1481 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: 0.1353. Min Range: -0.1353

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1180418 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1040773 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1119. Min Act: -0.0002

Data Index: 406484 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1150. Min Act: -0.0002

Data Index: 485760 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1062. Min Act: -0.0002

Data Index: 713511 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1076. Min Act: -0.0002

Data Index: 482411 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1106. Min Act: -0.0002

Data Index: 292907 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1019. Min Act: -0.0002

Data Index: 664906 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0996. Min Act: -0.0002

Data Index: 736443 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1001. Min Act: -0.0002

Data Index: 998932 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1021. Min Act: -0.0002

Data Index: 380491 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0974. Min Act: -0.0002

Data Index: 945653 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0988. Min Act: -0.0002

Data Index: 679926 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0948. Min Act: -0.0002

Data Index: 500272 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0913. Min Act: -0.0002

Data Index: 654861 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0941. Min Act: -0.0002

Data Index: 658141 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0914. Min Act: -0.0002

Data Index: 775878 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0947. Min Act: -0.0002

Data Index: 22465 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1164991 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0917. Min Act: -0.0002

Data Index: 98898 (C4 (Web Text))

Max Activating Token Index: 98