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

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

Neuron 4307 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.2580. Min Act: -0.0001

Data Index: 1642925 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1535028 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.2021. Min Act: -0.0001

Data Index: 257669 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1409133 (Python Code)

Max Activating Token Index: 749

Text #4

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1979. Min Act: -0.0001

Data Index: 107859 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1598066 (Python Code)

Max Activating Token Index: 218

Text #6

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1313587 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1765. Min Act: -0.0001

Data Index: 388357 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1669. Min Act: -0.0001

Data Index: 814345 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1852. Min Act: -0.0001

Data Index: 1072888 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1281804 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1791. Min Act: -0.0001

Data Index: 673708 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1381527 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1670. Min Act: -0.0001

Data Index: 740675 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1213798 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1470. Min Act: -0.0001

Data Index: 64131 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1399752 (Python Code)

Max Activating Token Index: 384

Text #17

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1220621 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1661. Min Act: -0.0001

Data Index: 1354152 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.2580. Min Range: -0.2580

Max Act: 0.1654. Min Act: -0.0001

Data Index: 726895 (C4 (Web Text))

Max Activating Token Index: 56