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

Dataset: The Pile

Neuron 4420 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: 1.2981. Min Range: -1.2981

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1820074 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0886. Min Act: -0.0000

Data Index: 260511 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.1160. Min Act: -0.0000

Data Index: 399668 (The Pile)

Max Activating Token Index: 871

Text #3

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1579826 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0827. Min Act: -0.0000

Data Index: 249373 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 1.2981. Min Range: -1.2981

Max Act: 1.0285. Min Act: -0.0000

Data Index: 819198 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9082. Min Act: -0.0000

Data Index: 54101 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1484877 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1859445 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1380436 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9723. Min Act: -0.0000

Data Index: 308416 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1586580 (The Pile)

Max Activating Token Index: 249

Text #12

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8217. Min Act: -0.0000

Data Index: 501273 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8739. Min Act: -0.0000

Data Index: 658176 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8645. Min Act: -0.0000

Data Index: 944487 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.7557. Min Act: -0.0000

Data Index: 908983 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1389074 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8246. Min Act: -0.0000

Data Index: 4914 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.7156. Min Act: -0.0000

Data Index: 776603 (The Pile)

Max Activating Token Index: 828

Text #19

Max Range: 1.2981. Min Range: -1.2981

Max Act: 0.8140. Min Act: -0.0000

Data Index: 329850 (The Pile)

Max Activating Token Index: 977