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

Dataset: The Pile

Neuron 3460 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: 0.9480. Min Range: -0.9480

Max Act: 0.9321. Min Act: -0.0000

Data Index: 641757 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1605818 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.9228. Min Act: -0.0000

Data Index: 157744 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.9055. Min Act: -0.0000

Data Index: 821988 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.9010. Min Act: -0.0000

Data Index: 298159 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1460611 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1769720 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8767. Min Act: -0.0000

Data Index: 724684 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1720404 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1812388 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8072. Min Act: -0.0000

Data Index: 498244 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1014921 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1891032 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1141721 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1070644 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1718070 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8517. Min Act: -0.0000

Data Index: 573821 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1701131 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1877627 (The Pile)

Max Activating Token Index: 944

Text #19

Max Range: 0.9480. Min Range: -0.9480

Max Act: 0.8290. Min Act: -0.0000

Data Index: 887488 (The Pile)

Max Activating Token Index: 442