Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3531 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1220923 (The Pile)

Max Activating Token Index: 481

Text #1

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1928297 (The Pile)

Max Activating Token Index: 541

Text #2

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1223. Min Act: -0.0000

Data Index: 131261 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1726419 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1745886 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1665300 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1304260 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1745689 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1114. Min Act: -0.0000

Data Index: 63684 (The Pile)

Max Activating Token Index: 539

Text #9

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1262155 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1142. Min Act: -0.0000

Data Index: 192 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1774079 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1563947 (The Pile)

Max Activating Token Index: 434

Text #13

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1492669 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1029. Min Act: -0.0000

Data Index: 732172 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1977875 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1034. Min Act: -0.0000

Data Index: 958819 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1906915 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1102. Min Act: -0.0000

Data Index: 353664 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1181. Min Act: -0.0000

Data Index: 481451 (The Pile)

Max Activating Token Index: 868