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

Dataset: The Pile

Neuron 1769 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1328. Min Act: -0.0000

Data Index: 267462 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1284. Min Act: -0.0000

Data Index: 653737 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1401125 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1168. Min Act: -0.0000

Data Index: 969221 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1232336 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1272. Min Act: -0.0000

Data Index: 440703 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.0879. Min Act: -0.0000

Data Index: 985959 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1659396 (The Pile)

Max Activating Token Index: 937

Text #8

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1091. Min Act: -0.0000

Data Index: 178653 (The Pile)

Max Activating Token Index: 829

Text #9

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1226075 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1551480 (The Pile)

Max Activating Token Index: 601

Text #11

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1162. Min Act: -0.0000

Data Index: 359106 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1087250 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1157. Min Act: -0.0000

Data Index: 125765 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1010. Min Act: -0.0000

Data Index: 158074 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1153. Min Act: -0.0000

Data Index: 781481 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1125. Min Act: -0.0000

Data Index: 966614 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1117. Min Act: -0.0000

Data Index: 273202 (The Pile)

Max Activating Token Index: 804

Text #18

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1327603 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 0.1613. Min Range: -0.1613

Max Act: 0.1053. Min Act: -0.0000

Data Index: 219450 (The Pile)

Max Activating Token Index: 457