Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2680 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.8274. Min Act: -0.0001

Data Index: 1032499 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.8039. Min Act: -0.0001

Data Index: 84764 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6885. Min Act: -0.0001

Data Index: 1046785 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6498. Min Act: -0.0001

Data Index: 879730 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.7015. Min Act: -0.0001

Data Index: 621169 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6829. Min Act: -0.0001

Data Index: 224656 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.5747. Min Act: -0.0001

Data Index: 851776 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.7166. Min Act: -0.0001

Data Index: 405666 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6368. Min Act: -0.0001

Data Index: 1206908 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6693. Min Act: -0.0001

Data Index: 647562 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6811. Min Act: -0.0001

Data Index: 54103 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6559. Min Act: -0.0001

Data Index: 59132 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6756. Min Act: -0.0001

Data Index: 387526 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6492. Min Act: -0.0001

Data Index: 1209319 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6216. Min Act: -0.0001

Data Index: 96434 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6417. Min Act: -0.0001

Data Index: 772534 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6220. Min Act: -0.0001

Data Index: 430367 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6998. Min Act: -0.0001

Data Index: 713554 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6658. Min Act: -0.0001

Data Index: 1047684 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.8274. Min Range: -0.8274

Max Act: 0.6069. Min Act: -0.0001

Data Index: 205849 (C4 (Web Text))

Max Activating Token Index: 345