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

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

Neuron 2970 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2294. Min Act: -0.0000

Data Index: 515457 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2081. Min Act: -0.0001

Data Index: 744508 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2167. Min Act: -0.0000

Data Index: 713834 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1237309 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2019. Min Act: -0.0000

Data Index: 101476 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2076. Min Act: -0.0000

Data Index: 324884 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1358599 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2012. Min Act: -0.0001

Data Index: 606429 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1927. Min Act: -0.0000

Data Index: 127101 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1918. Min Act: -0.0000

Data Index: 820437 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1270889 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1835. Min Act: -0.0000

Data Index: 644627 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1329108 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.2034. Min Act: -0.0000

Data Index: 757318 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1810. Min Act: 0.0000

Data Index: 492167 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1690. Min Act: -0.0000

Data Index: 838024 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1775. Min Act: -0.0000

Data Index: 493604 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1749. Min Act: -0.0001

Data Index: 919158 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1678. Min Act: -0.0001

Data Index: 357491 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.2294. Min Range: -0.2294

Max Act: 0.1805. Min Act: -0.0000

Data Index: 544807 (C4 (Web Text))

Max Activating Token Index: 143