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

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

Neuron 2144 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1262362 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.1888. Min Act: -0.0000

Data Index: 416595 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0405. Min Act: -0.0000

Data Index: 433902 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0848. Min Act: -0.0000

Data Index: 923447 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1022553 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.1020. Min Act: -0.0000

Data Index: 608150 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1298957 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9859. Min Act: -0.0000

Data Index: 731244 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0237. Min Act: -0.0000

Data Index: 964380 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0842. Min Act: -0.0000

Data Index: 486869 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9905. Min Act: -0.0000

Data Index: 661890 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0274. Min Act: -0.0000

Data Index: 492350 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1340800 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0542. Min Act: -0.0000

Data Index: 143381 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1336472 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9542. Min Act: -0.0000

Data Index: 144392 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.2531. Min Range: -1.2531

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1315505 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9148. Min Act: -0.0000

Data Index: 89254 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9141. Min Act: -0.0000

Data Index: 327250 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 1.2531. Min Range: -1.2531

Max Act: 0.9972. Min Act: -0.0000

Data Index: 358234 (C4 (Web Text))

Max Activating Token Index: 80