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

Dataset: The Pile

Neuron 3429 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1344363 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7027. Min Act: -0.0000

Data Index: 356054 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6768. Min Act: -0.0000

Data Index: 635964 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7127. Min Act: -0.0000

Data Index: 215951 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7241. Min Act: -0.0000

Data Index: 518115 (The Pile)

Max Activating Token Index: 767

Text #5

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6947. Min Act: -0.0000

Data Index: 528454 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1238530 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1367574 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1883783 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1342422 (The Pile)

Max Activating Token Index: 829

Text #10

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7919. Min Act: -0.0000

Data Index: 112377 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1562768 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1629736 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1047797 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6286. Min Act: -0.0000

Data Index: 650057 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6190. Min Act: -0.0000

Data Index: 67903 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1129108 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1097534 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.5704. Min Act: -0.0000

Data Index: 989862 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6072. Min Act: -0.0000

Data Index: 753382 (The Pile)

Max Activating Token Index: 86