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

Dataset: The Pile

Neuron 1087 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9725. Min Range: -7.9725

Max Act: 7.9725. Min Act: -0.0000

Data Index: 1624397 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 7.9725. Min Range: -7.9725

Max Act: 7.9436. Min Act: -0.0000

Data Index: 96965 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 7.9725. Min Range: -7.9725

Max Act: 7.6490. Min Act: -0.0000

Data Index: 1865918 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.6703. Min Act: -0.0000

Data Index: 1925505 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 7.9725. Min Range: -7.9725

Max Act: 7.6679. Min Act: -0.0000

Data Index: 796746 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 7.9725. Min Range: -7.9725

Max Act: 7.0261. Min Act: -0.0000

Data Index: 45467 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.5707. Min Act: -0.0000

Data Index: 962328 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 7.9725. Min Range: -7.9725

Max Act: 7.1077. Min Act: -0.0000

Data Index: 303991 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 7.9725. Min Range: -7.9725

Max Act: 7.4109. Min Act: -0.0000

Data Index: 209840 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 7.9725. Min Range: -7.9725

Max Act: 7.0672. Min Act: -0.0000

Data Index: 1711453 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.9544. Min Act: -0.0000

Data Index: 1932831 (The Pile)

Max Activating Token Index: 711

Text #11

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.9150. Min Act: 0.0001

Data Index: 1312515 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.9400. Min Act: -0.0000

Data Index: 1951808 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.7376. Min Act: -0.0000

Data Index: 1290057 (The Pile)

Max Activating Token Index: 870

Text #14

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.4831. Min Act: -0.0000

Data Index: 826047 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.6461. Min Act: -0.0000

Data Index: 1704784 (The Pile)

Max Activating Token Index: 505

Text #16

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.3925. Min Act: -0.0000

Data Index: 192037 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.5622. Min Act: -0.0000

Data Index: 568816 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.5929. Min Act: -0.0000

Data Index: 1495617 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 7.9725. Min Range: -7.9725

Max Act: 6.7356. Min Act: -0.0000

Data Index: 1232210 (The Pile)

Max Activating Token Index: 936