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

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

Neuron 560 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1798. Min Range: -3.1798

Max Act: 3.1798. Min Act: -0.0000

Data Index: 1311625 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 3.1798. Min Range: -3.1798

Max Act: 2.8029. Min Act: -0.0000

Data Index: 59986 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.9585. Min Act: -0.0000

Data Index: 440893 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 3.1798. Min Range: -3.1798

Max Act: 2.1481. Min Act: -0.0000

Data Index: 1201850 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 3.1798. Min Range: -3.1798

Max Act: 2.5238. Min Act: -0.0000

Data Index: 1292356 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.8779. Min Act: -0.0000

Data Index: 498492 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.7826. Min Act: -0.0000

Data Index: 1328727 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.9592. Min Act: -0.0000

Data Index: 191664 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 3.1798. Min Range: -3.1798

Max Act: 2.0432. Min Act: -0.0000

Data Index: 677477 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.7299. Min Act: -0.0001

Data Index: 248552 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.8646. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 3.1798. Min Range: -3.1798

Max Act: 2.0103. Min Act: -0.0000

Data Index: 325456 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.8243. Min Act: -0.0001

Data Index: 18372 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.9009. Min Act: -0.0001

Data Index: 1307743 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.8004. Min Act: -0.0001

Data Index: 1327203 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.9185. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.6905. Min Act: -0.0000

Data Index: 1027450 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.8054. Min Act: -0.0000

Data Index: 1020635 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.6789. Min Act: -0.0001

Data Index: 1275895 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 3.1798. Min Range: -3.1798

Max Act: 1.6637. Min Act: -0.0001

Data Index: 996257 (C4 (Web Text))

Max Activating Token Index: 618