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

Dataset: The Pile

Neuron 4491 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: 1.1777. Min Range: -1.1777

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1118744 (The Pile)

Max Activating Token Index: 696

Text #1

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1190543 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.8838. Min Act: -0.0000

Data Index: 764685 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.7585. Min Act: -0.0000

Data Index: 119936 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1823272 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1633298 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1239889 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6875. Min Act: -0.0000

Data Index: 886867 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1829165 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6886. Min Act: -0.0000

Data Index: 318294 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1595746 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1114266 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6840. Min Act: -0.0000

Data Index: 1171957 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1788867 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.7244. Min Act: -0.0000

Data Index: 316117 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1500095 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6287. Min Act: -0.0000

Data Index: 820500 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6726. Min Act: -0.0000

Data Index: 600142 (The Pile)

Max Activating Token Index: 926

Text #18

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1438193 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.1777. Min Range: -1.1777

Max Act: 0.6286. Min Act: -0.0000

Data Index: 737073 (The Pile)

Max Activating Token Index: 555