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

Dataset: The Pile

Neuron 608 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1653477 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1831692 (The Pile)

Max Activating Token Index: 660

Text #2

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4663. Min Act: -0.0000

Data Index: 868681 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4776. Min Act: -0.0000

Data Index: 977401 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1810936 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1783114 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1054883 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4060. Min Act: -0.0000

Data Index: 54576 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1402289 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1435072 (The Pile)

Max Activating Token Index: 790

Text #10

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4222. Min Act: -0.0000

Data Index: 522720 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4044. Min Act: -0.0000

Data Index: 398744 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4229. Min Act: -0.0000

Data Index: 13341 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1348823 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1401741 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4243. Min Act: -0.0000

Data Index: 798177 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4006. Min Act: -0.0000

Data Index: 972661 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4126. Min Act: -0.0000

Data Index: 509421 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3799. Min Act: -0.0000

Data Index: 867005 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3910. Min Act: -0.0000

Data Index: 298037 (The Pile)

Max Activating Token Index: 694