Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2588 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1787. Min Range: -1.1787

Max Act: 1.1787. Min Act: -0.0000

Data Index: 196281 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 1.1787. Min Range: -1.1787

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1917245 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1462592 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1349017 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 1.1787. Min Range: -1.1787

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1381554 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1414005 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: 1.1787. Min Range: -1.1787

Max Act: 1.0066. Min Act: 0.0000

Data Index: 430441 (The Pile)

Max Activating Token Index: 828

Text #7

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9216. Min Act: -0.0000

Data Index: 643478 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9531. Min Act: -0.0000

Data Index: 222908 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1901357 (The Pile)

Max Activating Token Index: 659

Text #10

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.9512. Min Act: -0.0000

Data Index: 727540 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1522706 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8924. Min Act: -0.0000

Data Index: 841768 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8334. Min Act: 0.0002

Data Index: 10751 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1342514 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1867542 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8338. Min Act: -0.0000

Data Index: 885968 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8003. Min Act: -0.0000

Data Index: 177795 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8303. Min Act: -0.0000

Data Index: 261018 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 1.1787. Min Range: -1.1787

Max Act: 0.8067. Min Act: -0.0000

Data Index: 579926 (The Pile)

Max Activating Token Index: 670