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

Dataset: The Pile

Neuron 1495 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: 4.0645. Min Range: -4.0645

Max Act: 3.8779. Min Act: -0.0000

Data Index: 1332299 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 4.0645. Min Range: -4.0645

Max Act: 4.0645. Min Act: -0.0000

Data Index: 549516 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.8889. Min Act: -0.0000

Data Index: 204908 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 4.0645. Min Range: -4.0645

Max Act: 4.0532. Min Act: -0.0000

Data Index: 1865469 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.3637. Min Act: -0.0000

Data Index: 855589 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.5746. Min Act: -0.0000

Data Index: 1312898 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.5287. Min Act: -0.0000

Data Index: 569967 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.5855. Min Act: -0.0000

Data Index: 1845400 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.4667. Min Act: -0.0000

Data Index: 446124 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 4.0645. Min Range: -4.0645

Max Act: 2.8560. Min Act: -0.0000

Data Index: 665677 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 4.0645. Min Range: -4.0645

Max Act: 2.8500. Min Act: -0.0000

Data Index: 1509833 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.4114. Min Act: -0.0000

Data Index: 1656181 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.1429. Min Act: -0.0000

Data Index: 909742 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.0277. Min Act: -0.0000

Data Index: 1886307 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 4.0645. Min Range: -4.0645

Max Act: 2.9358. Min Act: -0.0000

Data Index: 1996741 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 4.0645. Min Range: -4.0645

Max Act: 2.9792. Min Act: -0.0000

Data Index: 1786729 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.0871. Min Act: -0.0000

Data Index: 872486 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 4.0645. Min Range: -4.0645

Max Act: 2.7660. Min Act: -0.0000

Data Index: 1267801 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 4.0645. Min Range: -4.0645

Max Act: 3.2097. Min Act: -0.0000

Data Index: 1473192 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 4.0645. Min Range: -4.0645

Max Act: 2.7435. Min Act: -0.0000

Data Index: 277095 (The Pile)

Max Activating Token Index: 76