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

Dataset: The Pile

Neuron 139 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3621. Min Act: -0.0000

Data Index: 16474 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2532. Min Act: -0.0000

Data Index: 619846 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.1838. Min Act: -0.0000

Data Index: 467891 (The Pile)

Max Activating Token Index: 17

Text #3

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.1776. Min Act: -0.0000

Data Index: 935718 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.1969. Min Act: -0.0000

Data Index: 194819 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1003709 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0971. Min Act: -0.0000

Data Index: 645969 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1391829 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1596478 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0261. Min Act: -0.0000

Data Index: 135043 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1867587 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0733. Min Act: -0.0000

Data Index: 82610 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1837433 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1169075 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0265. Min Act: -0.0000

Data Index: 1400480 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1296781 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1502134 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1990877 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.9093. Min Act: -0.0000

Data Index: 983233 (The Pile)

Max Activating Token Index: 10

Text #19

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1779669 (The Pile)

Max Activating Token Index: 933