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

Dataset: The Pile

Neuron 3523 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: 0.1193. Min Range: -0.1193

Max Act: 0.1156. Min Act: -0.0000

Data Index: 761688 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1113827 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1193. Min Act: -0.0000

Data Index: 246752 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1086. Min Act: -0.0000

Data Index: 991817 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1120. Min Act: -0.0000

Data Index: 253342 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1209557 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1135293 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1077125 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1447201 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1457342 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1001. Min Act: -0.0000

Data Index: 605395 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1654928 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1027638 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0954. Min Act: -0.0000

Data Index: 983822 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0980. Min Act: -0.0000

Data Index: 30107 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0948. Min Act: -0.0000

Data Index: 20154 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1379632 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1743249 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0967. Min Act: -0.0000

Data Index: 10106 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0999. Min Act: -0.0000

Data Index: 12710 (The Pile)

Max Activating Token Index: 529