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

Dataset: The Pile

Neuron 493 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: 1.2635. Min Range: -1.2635

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1110020 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8515. Min Act: -0.0000

Data Index: 336352 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1558982 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8471. Min Act: -0.0000

Data Index: 704106 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8797. Min Act: -0.0000

Data Index: 727206 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1913540 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1290619 (The Pile)

Max Activating Token Index: 876

Text #7

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1472246 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8840. Min Act: -0.0000

Data Index: 701281 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1420156 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8803. Min Act: -0.0000

Data Index: 215500 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1257669 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7251. Min Act: -0.0000

Data Index: 681299 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7657. Min Act: -0.0000

Data Index: 73624 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1954744 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7926. Min Act: -0.0000

Data Index: 135352 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1115427 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1023214 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1103009 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 1.2635. Min Range: -1.2635

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1922495 (The Pile)

Max Activating Token Index: 16