Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2221 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1012841 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1121. Min Act: -0.0000

Data Index: 582253 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1150. Min Act: -0.0000

Data Index: 25905 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1115. Min Act: -0.0001

Data Index: 651016 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1142. Min Act: -0.0001

Data Index: 1149086 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0987. Min Act: -0.0000

Data Index: 458310 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1351568 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1014. Min Act: -0.0000

Data Index: 66583 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1048. Min Act: -0.0000

Data Index: 428708 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0893. Min Act: -0.0000

Data Index: 52382 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1002. Min Act: -0.0001

Data Index: 35195 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0952. Min Act: -0.0001

Data Index: 898733 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0969. Min Act: -0.0001

Data Index: 423293 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0911. Min Act: -0.0000

Data Index: 802958 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1357114 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0909. Min Act: -0.0000

Data Index: 738311 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0908. Min Act: -0.0001

Data Index: 851723 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0925. Min Act: -0.0001

Data Index: 97475 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.1024. Min Act: -0.0000

Data Index: 73061 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.1517. Min Range: -0.1517

Max Act: 0.0883. Min Act: -0.0000

Data Index: 335722 (C4 (Web Text))

Max Activating Token Index: 520