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

Dataset: The Pile

Neuron 3104 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: 1.9537. Min Range: -1.9537

Max Act: 1.8231. Min Act: -0.0000

Data Index: 27793 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.9537. Min Act: -0.0000

Data Index: 631775 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1402728 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6794. Min Act: -0.0000

Data Index: 677567 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1837427 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1148572 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1630365 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4728. Min Act: -0.0000

Data Index: 244026 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6886. Min Act: -0.0000

Data Index: 686556 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4855. Min Act: -0.0000

Data Index: 465215 (The Pile)

Max Activating Token Index: 335

Text #10

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.5422. Min Act: -0.0000

Data Index: 384896 (The Pile)

Max Activating Token Index: 992

Text #11

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.5932. Min Act: -0.0000

Data Index: 82581 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1659836 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4706. Min Act: -0.0000

Data Index: 333131 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1628201 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4756. Min Act: 0.0000

Data Index: 1069467 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.5939. Min Act: -0.0000

Data Index: 384580 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.2359. Min Act: 0.0000

Data Index: 1255388 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.4670. Min Act: -0.0000

Data Index: 842865 (The Pile)

Max Activating Token Index: 822

Text #19

Max Range: 1.9537. Min Range: -1.9537

Max Act: 1.5264. Min Act: -0.0000

Data Index: 470928 (The Pile)

Max Activating Token Index: 782