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

Dataset: The Pile

Neuron 2987 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1017477 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1980. Min Act: -0.0000

Data Index: 105850 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1666470 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1385713 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1494678 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1252259 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.2058. Min Act: -0.0000

Data Index: 183280 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1401216 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1813723 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1630. Min Act: -0.0000

Data Index: 668411 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1232631 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1737. Min Act: -0.0000

Data Index: 435468 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1116048 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1611062 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1520. Min Act: -0.0000

Data Index: 229183 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1918645 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1714614 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1698301 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1604. Min Act: -0.0000

Data Index: 170153 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1266240 (The Pile)

Max Activating Token Index: 874