Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4956 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9574. Min Range: -2.9574

Max Act: 2.9574. Min Act: -0.0000

Data Index: 532969 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 2.9574. Min Range: -2.9574

Max Act: 2.1417. Min Act: -0.0000

Data Index: 831409 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 2.9574. Min Range: -2.9574

Max Act: 2.1381. Min Act: -0.0000

Data Index: 478246 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.9355. Min Act: 0.0000

Data Index: 729489 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.9756. Min Act: -0.0000

Data Index: 1048548 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.9105. Min Act: -0.0000

Data Index: 973547 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.7985. Min Act: -0.0000

Data Index: 207829 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.9042. Min Act: -0.0000

Data Index: 17062 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.9016. Min Act: -0.0000

Data Index: 866999 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.7649. Min Act: -0.0000

Data Index: 417929 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.7385. Min Act: -0.0000

Data Index: 602440 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.7262. Min Act: 0.0001

Data Index: 710645 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.7126. Min Act: -0.0000

Data Index: 120911 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.7118. Min Act: -0.0000

Data Index: 9236 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.7996. Min Act: 0.0000

Data Index: 961877 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.6111. Min Act: -0.0000

Data Index: 831620 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.6751. Min Act: -0.0000

Data Index: 900805 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.5885. Min Act: -0.0000

Data Index: 440152 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.6729. Min Act: -0.0000

Data Index: 347603 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 2.9574. Min Range: -2.9574

Max Act: 1.6718. Min Act: 0.0001

Data Index: 1149205 (C4 (Web Text))

Max Activating Token Index: 911