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

Dataset: The Pile

Neuron 344 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: 0.5609. Min Range: -0.5609

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1227253 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.5609. Min Act: -0.0000

Data Index: 461273 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1733677 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1148444 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4305. Min Act: -0.0000

Data Index: 780977 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1468871 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4449. Min Act: -0.0000

Data Index: 314883 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4075. Min Act: -0.0000

Data Index: 947980 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1774279 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4084. Min Act: -0.0000

Data Index: 921679 (The Pile)

Max Activating Token Index: 559

Text #10

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4365. Min Act: -0.0000

Data Index: 742114 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4389. Min Act: -0.0000

Data Index: 318253 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4087. Min Act: -0.0000

Data Index: 1910057 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1319752 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1394494 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4244. Min Act: -0.0000

Data Index: 32299 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1159046 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.4262. Min Act: -0.0000

Data Index: 293449 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1997584 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 0.5609. Min Range: -0.5609

Max Act: 0.3649. Min Act: -0.0000

Data Index: 41126 (The Pile)

Max Activating Token Index: 398