Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3832 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2211. Min Act: -0.0000

Data Index: 463179 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2144. Min Act: -0.0000

Data Index: 565767 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1281538 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1009381 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1985. Min Act: -0.0001

Data Index: 435518 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1808. Min Act: -0.0000

Data Index: 466298 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1675. Min Act: -0.0000

Data Index: 920748 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1808. Min Act: -0.0000

Data Index: 294228 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1276728 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1219479 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1194547 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1693. Min Act: -0.0000

Data Index: 614558 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1781. Min Act: -0.0001

Data Index: 45718 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1709. Min Act: -0.0000

Data Index: 92790 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1604. Min Act: -0.0000

Data Index: 867552 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1225671 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1561. Min Act: -0.0001

Data Index: 406216 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1198387 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1304553 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1524. Min Act: -0.0001

Data Index: 539527 (C4 (Web Text))

Max Activating Token Index: 327