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

Dataset: The Pile

Neuron 477 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: 0.1650. Min Range: -0.1650

Max Act: 0.1650. Min Act: 0.0001

Data Index: 1350566 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1311. Min Act: -0.0000

Data Index: 688073 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1653004 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1721590 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1468683 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1185. Min Act: -0.0000

Data Index: 554622 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1161. Min Act: 0.0000

Data Index: 919738 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1978939 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1875585 (The Pile)

Max Activating Token Index: 915

Text #9

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1258792 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1020. Min Act: 0.0000

Data Index: 1331651 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1021. Min Act: -0.0000

Data Index: 612220 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1652304 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1075207 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0936. Min Act: 0.0000

Data Index: 1467100 (The Pile)

Max Activating Token Index: 988

Text #15

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1938836 (The Pile)

Max Activating Token Index: 842

Text #16

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0996. Min Act: 0.0000

Data Index: 884717 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0999. Min Act: 0.0000

Data Index: 1718195 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0967. Min Act: 0.0000

Data Index: 1513639 (The Pile)

Max Activating Token Index: 975

Text #19

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.0944. Min Act: 0.0000

Data Index: 980333 (The Pile)

Max Activating Token Index: 956