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

Dataset: The Pile

Neuron 1878 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1277899 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1118993 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1165117 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6531. Min Act: -0.0000

Data Index: 781747 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6240. Min Act: -0.0000

Data Index: 66748 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5917. Min Act: -0.0000

Data Index: 286307 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1934906 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5732. Min Act: -0.0000

Data Index: 634898 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.6179. Min Act: -0.0000

Data Index: 93450 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1077995 (The Pile)

Max Activating Token Index: 204

Text #10

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5824. Min Act: -0.0000

Data Index: 360304 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1717322 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5713. Min Act: 0.0000

Data Index: 661245 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1414689 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5385. Min Act: -0.0000

Data Index: 838193 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5433. Min Act: 0.0000

Data Index: 1387740 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1724729 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1810669 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5302. Min Act: -0.0000

Data Index: 35958 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.8829. Min Range: -0.8829

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1149896 (The Pile)

Max Activating Token Index: 977