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

Dataset: The Pile

Neuron 408 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1779632 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1672808 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.5621. Min Act: -0.0000

Data Index: 331387 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1300120 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1389390 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1704877 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4571. Min Act: -0.0000

Data Index: 507355 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.5047. Min Act: -0.0000

Data Index: 958539 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4902. Min Act: -0.0000

Data Index: 760860 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1247587 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4984. Min Act: -0.0000

Data Index: 324289 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1974483 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.5007. Min Act: -0.0000

Data Index: 497589 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1753514 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4726. Min Act: -0.0000

Data Index: 81645 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1647705 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1505130 (The Pile)

Max Activating Token Index: 103

Text #17

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1078169 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1541807 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 0.6725. Min Range: -0.6725

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1407511 (The Pile)

Max Activating Token Index: 31