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

Dataset: The Pile

Neuron 3348 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: 6.1883. Min Range: -6.1883

Max Act: 6.1579. Min Act: -0.0000

Data Index: 380057 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 6.1883. Min Range: -6.1883

Max Act: 6.1219. Min Act: -0.0000

Data Index: 813749 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.6066. Min Act: -0.0000

Data Index: 1998524 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 6.1883. Min Range: -6.1883

Max Act: 6.1883. Min Act: -0.0000

Data Index: 1199408 (The Pile)

Max Activating Token Index: 656

Text #4

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.6570. Min Act: -0.0000

Data Index: 1902780 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.8488. Min Act: -0.0000

Data Index: 519372 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.9902. Min Act: -0.0000

Data Index: 1491794 (The Pile)

Max Activating Token Index: 793

Text #7

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.8183. Min Act: -0.0000

Data Index: 1698523 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 6.1883. Min Range: -6.1883

Max Act: 6.1775. Min Act: -0.0000

Data Index: 1580328 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 6.1883. Min Range: -6.1883

Max Act: 6.1684. Min Act: -0.0000

Data Index: 150777 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.2836. Min Act: -0.0000

Data Index: 87853 (The Pile)

Max Activating Token Index: 462

Text #11

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.6425. Min Act: -0.0000

Data Index: 1545447 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.8079. Min Act: -0.0000

Data Index: 1423543 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.9911. Min Act: -0.0000

Data Index: 561757 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.3686. Min Act: -0.0000

Data Index: 724734 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.7374. Min Act: -0.0000

Data Index: 975959 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.8865. Min Act: -0.0000

Data Index: 322730 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.2964. Min Act: -0.0000

Data Index: 351062 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.8070. Min Act: -0.0000

Data Index: 1294897 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 6.1883. Min Range: -6.1883

Max Act: 5.6362. Min Act: -0.0000

Data Index: 1363017 (The Pile)

Max Activating Token Index: 11