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

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

Neuron 637 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2370. Min Act: -0.0001

Data Index: 728554 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2130. Min Act: -0.0001

Data Index: 627353 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2049. Min Act: -0.0001

Data Index: 99095 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1929. Min Act: -0.0001

Data Index: 42986 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1020308 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1974. Min Act: -0.0000

Data Index: 641659 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1204503 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1792. Min Act: -0.0001

Data Index: 907097 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1878. Min Act: -0.0001

Data Index: 742584 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1014328 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1906. Min Act: -0.0001

Data Index: 638651 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1802. Min Act: -0.0001

Data Index: 829838 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1161305 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1345077 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1677. Min Act: -0.0001

Data Index: 1283730 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1348685 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1752. Min Act: -0.0001

Data Index: 124243 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1122658 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1684. Min Act: -0.0001

Data Index: 105029 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1159738 (C4 (Web Text))

Max Activating Token Index: 197