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

Dataset: The Pile

Neuron 2198 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: 0.9896. Min Range: -0.9896

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1587698 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9348. Min Act: -0.0000

Data Index: 1767320 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9269. Min Act: -0.0000

Data Index: 509697 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8335. Min Act: -0.0000

Data Index: 270623 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8261. Min Act: -0.0000

Data Index: 116070 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1720387 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7955. Min Act: -0.0000

Data Index: 235528 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1544690 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7547. Min Act: -0.0000

Data Index: 979801 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7529. Min Act: -0.0000

Data Index: 139279 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7294. Min Act: -0.0000

Data Index: 951374 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1986010 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6478. Min Act: 0.0000

Data Index: 325856 (The Pile)

Max Activating Token Index: 723

Text #13

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7633. Min Act: -0.0000

Data Index: 64802 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1569580 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1585531 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8269. Min Act: -0.0000

Data Index: 577324 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1127181 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1183683 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1761661 (The Pile)

Max Activating Token Index: 118