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

Dataset: The Pile

Neuron 4567 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0594. Min Range: -1.0594

Max Act: 1.0594. Min Act: -0.0000

Data Index: 744921 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7741. Min Act: -0.0000

Data Index: 442845 (The Pile)

Max Activating Token Index: 950

Text #2

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1059126 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1485339 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6472. Min Act: -0.0000

Data Index: 509451 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1921467 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6091. Min Act: -0.0000

Data Index: 599795 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1509932 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1032716 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1944903 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1567756 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.5359. Min Act: -0.0000

Data Index: 38552 (The Pile)

Max Activating Token Index: 941

Text #12

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.5675. Min Act: -0.0000

Data Index: 601803 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1450518 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.5563. Min Act: -0.0000

Data Index: 755105 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1643372 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1433190 (The Pile)

Max Activating Token Index: 788

Text #17

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1460070 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1825243 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 1.0594. Min Range: -1.0594

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1509120 (The Pile)

Max Activating Token Index: 727