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

Dataset: The Pile

Neuron 2509 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: 1.1273. Min Range: -1.1273

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1917813 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1002089 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0582. Min Act: -0.0000

Data Index: 635522 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1674687 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0174. Min Act: -0.0000

Data Index: 236741 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1783184 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9987. Min Act: -0.0000

Data Index: 29429 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8352. Min Act: -0.0000

Data Index: 832282 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1712421 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9225. Min Act: -0.0000

Data Index: 610166 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8357. Min Act: -0.0000

Data Index: 724593 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1185372 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1879785 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.7863. Min Act: -0.0000

Data Index: 167307 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8789. Min Act: -0.0000

Data Index: 399383 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8067. Min Act: -0.0000

Data Index: 181081 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8396. Min Act: -0.0000

Data Index: 383905 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1322946 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1366704 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1748633 (The Pile)

Max Activating Token Index: 470