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

Dataset: The Pile

Neuron 2886 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: 3.1492. Min Range: -3.1492

Max Act: 3.1492. Min Act: -0.0000

Data Index: 934030 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.9886. Min Act: -0.0000

Data Index: 1941818 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.9177. Min Act: -0.0000

Data Index: 1434443 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 3.1492. Min Range: -3.1492

Max Act: 3.0446. Min Act: -0.0000

Data Index: 210155 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.7016. Min Act: -0.0000

Data Index: 1501431 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.7548. Min Act: -0.0000

Data Index: 63947 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.7053. Min Act: -0.0000

Data Index: 1773529 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.6550. Min Act: -0.0000

Data Index: 1080305 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.5832. Min Act: -0.0000

Data Index: 1613610 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.5027. Min Act: -0.0000

Data Index: 1509233 (The Pile)

Max Activating Token Index: 239

Text #10

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.6110. Min Act: -0.0000

Data Index: 1914611 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.5824. Min Act: -0.0000

Data Index: 1695867 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 3.1492. Min Range: -3.1492

Max Act: 2.1417. Min Act: -0.0000

Data Index: 1597757 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 3.1492. Min Range: -3.1492

Max Act: 1.5688. Min Act: -0.0000

Data Index: 705558 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 3.1492. Min Range: -3.1492

Max Act: 1.5306. Min Act: -0.0000

Data Index: 1890885 (The Pile)

Max Activating Token Index: 199

Text #15

Max Range: 3.1492. Min Range: -3.1492

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1225001 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 3.1492. Min Range: -3.1492

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1226417 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 3.1492. Min Range: -3.1492

Max Act: 1.0629. Min Act: -0.0000

Data Index: 199460 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 3.1492. Min Range: -3.1492

Max Act: 1.0961. Min Act: -0.0000

Data Index: 196914 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 3.1492. Min Range: -3.1492

Max Act: 0.9695. Min Act: -0.0000

Data Index: 124624 (The Pile)

Max Activating Token Index: 203