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

Dataset: The Pile

Neuron 4118 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8797. Min Range: -4.8797

Max Act: 4.8797. Min Act: -0.0000

Data Index: 1152276 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 4.8797. Min Range: -4.8797

Max Act: 4.0715. Min Act: -0.0000

Data Index: 1437506 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 4.8797. Min Range: -4.8797

Max Act: 4.3683. Min Act: -0.0000

Data Index: 1452167 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 4.8797. Min Range: -4.8797

Max Act: 4.1468. Min Act: -0.0000

Data Index: 1501656 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 4.8797. Min Range: -4.8797

Max Act: 4.0646. Min Act: -0.0000

Data Index: 378216 (The Pile)

Max Activating Token Index: 788

Text #5

Max Range: 4.8797. Min Range: -4.8797

Max Act: 4.3897. Min Act: -0.0000

Data Index: 500586 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.9555. Min Act: -0.0000

Data Index: 1808518 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.7825. Min Act: -0.0000

Data Index: 1523494 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.9501. Min Act: -0.0000

Data Index: 765018 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.7763. Min Act: -0.0000

Data Index: 67728 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.7578. Min Act: -0.0000

Data Index: 100383 (The Pile)

Max Activating Token Index: 723

Text #11

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.9226. Min Act: -0.0000

Data Index: 1549054 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.8730. Min Act: -0.0000

Data Index: 1059272 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.8112. Min Act: -0.0000

Data Index: 1743039 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.8054. Min Act: -0.0000

Data Index: 280833 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.6110. Min Act: -0.0000

Data Index: 980685 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.6243. Min Act: -0.0000

Data Index: 628181 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.7803. Min Act: -0.0000

Data Index: 961978 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.9359. Min Act: -0.0000

Data Index: 1907251 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 4.8797. Min Range: -4.8797

Max Act: 3.9056. Min Act: -0.0000

Data Index: 814990 (The Pile)

Max Activating Token Index: 622