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

Dataset: The Pile

Neuron 2440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2794. Min Act: -0.0000

Data Index: 879053 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2563. Min Act: -0.0000

Data Index: 631159 (The Pile)

Max Activating Token Index: 722

Text #2

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2588. Min Act: -0.0000

Data Index: 256227 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1646428 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1634999 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2187. Min Act: -0.0000

Data Index: 283329 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1127287 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1941732 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1998386 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2262. Min Act: -0.0000

Data Index: 1449358 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1424759 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2085. Min Act: -0.0000

Data Index: 129956 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1989846 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2045. Min Act: -0.0000

Data Index: 1655515 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1546441 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2062. Min Act: -0.0000

Data Index: 334779 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1009503 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.2000. Min Act: -0.0000

Data Index: 604156 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1904. Min Act: -0.0000

Data Index: 81322 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.2794. Min Range: -0.2794

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1801667 (The Pile)

Max Activating Token Index: 1009