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

Dataset: The Pile

Neuron 3342 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1237933 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7541. Min Act: -0.0000

Data Index: 886676 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7439. Min Act: -0.0000

Data Index: 372038 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6776. Min Act: -0.0000

Data Index: 179857 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.7250. Min Act: -0.0000

Data Index: 195915 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6549. Min Act: -0.0000

Data Index: 295469 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6705. Min Act: -0.0000

Data Index: 557549 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6734. Min Act: -0.0000

Data Index: 808262 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1385672 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6607. Min Act: -0.0000

Data Index: 329112 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6092. Min Act: -0.0000

Data Index: 859205 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1350036 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6436. Min Act: -0.0000

Data Index: 627605 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6009. Min Act: -0.0000

Data Index: 430447 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1996128 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1666007 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5973. Min Act: -0.0000

Data Index: 321785 (The Pile)

Max Activating Token Index: 844

Text #17

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5506. Min Act: -0.0000

Data Index: 973380 (The Pile)

Max Activating Token Index: 878

Text #18

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1439704 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 0.8623. Min Range: -0.8623

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1491334 (The Pile)

Max Activating Token Index: 399