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

Dataset: The Pile

Neuron 671 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.1588. Min Act: 0.0000

Data Index: 95087 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.7571. Min Act: -0.0000

Data Index: 147453 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.6879. Min Act: -0.0000

Data Index: 849451 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1296243 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1407293 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.6438. Min Act: -0.0000

Data Index: 1380214 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1177537 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5784. Min Act: -0.0000

Data Index: 687622 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.6226. Min Act: -0.0000

Data Index: 698034 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1995197 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1717828 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1517435 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5541. Min Act: -0.0000

Data Index: 473514 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5414. Min Act: -0.0000

Data Index: 308171 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1634059 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5793. Min Act: -0.0000

Data Index: 634729 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5565. Min Act: -0.0000

Data Index: 246340 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5673. Min Act: -0.0000

Data Index: 698043 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1168080 (The Pile)

Max Activating Token Index: 549

Text #19

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1640043 (The Pile)

Max Activating Token Index: 995