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

Dataset: The Pile

Neuron 1620 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.3760. Min Act: -0.0000

Data Index: 206012 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.1734. Min Act: -0.0000

Data Index: 328269 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.1506. Min Act: -0.0000

Data Index: 104323 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.1814. Min Act: -0.0000

Data Index: 634082 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0208. Min Act: -0.0000

Data Index: 363214 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1052591 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0695. Min Act: -0.0000

Data Index: 781708 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0800. Min Act: -0.0001

Data Index: 259723 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1145366 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1281503 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1426729 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1832182 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1233086 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0294. Min Act: -0.0000

Data Index: 245147 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9786. Min Act: -0.0000

Data Index: 910550 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1987144 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1558593 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9561. Min Act: -0.0000

Data Index: 322839 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1592395 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1686341 (The Pile)

Max Activating Token Index: 470