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

Dataset: The Pile

Neuron 1572 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: 1.6342. Min Range: -1.6342

Max Act: 1.5549. Min Act: -0.0000

Data Index: 117310 (The Pile)

Max Activating Token Index: 712

Text #1

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.5048. Min Act: -0.0000

Data Index: 920052 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.5276. Min Act: -0.0000

Data Index: 702931 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1397046 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.4088. Min Act: -0.0000

Data Index: 307713 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.2375. Min Act: -0.0000

Data Index: 982158 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.5015. Min Act: -0.0000

Data Index: 42805 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.3340. Min Act: -0.0000

Data Index: 1412506 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.3376. Min Act: -0.0000

Data Index: 631966 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.6342. Min Act: -0.0000

Data Index: 795533 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.4808. Min Act: -0.0000

Data Index: 1615489 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1314077 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.0776. Min Act: -0.0000

Data Index: 421011 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.1840. Min Act: -0.0000

Data Index: 322027 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1482229 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1361296 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.0435. Min Act: -0.0000

Data Index: 124024 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1416528 (The Pile)

Max Activating Token Index: 694

Text #18

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.1469. Min Act: -0.0000

Data Index: 47151 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 1.6342. Min Range: -1.6342

Max Act: 1.0684. Min Act: -0.0000

Data Index: 766968 (The Pile)

Max Activating Token Index: 929