Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 723 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1065966 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1031644 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1112606 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1915. Min Act: -0.0001

Data Index: 965012 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1728. Min Act: -0.0001

Data Index: 966977 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1000520 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1696. Min Act: -0.0001

Data Index: 353289 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1814. Min Act: -0.0001

Data Index: 6666 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1056926 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1663. Min Act: -0.0001

Data Index: 665854 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1352538 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1489418 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1375359 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1598. Min Act: -0.0001

Data Index: 825028 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1651. Min Act: -0.0001

Data Index: 613971 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1409757 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1524. Min Act: -0.0001

Data Index: 195948 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1634. Min Act: -0.0001

Data Index: 54312 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1571. Min Act: -0.0001

Data Index: 74149 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1514. Min Act: -0.0001

Data Index: 248641 (C4 (Web Text))

Max Activating Token Index: 789