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

Dataset: The Pile

Neuron 1989 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: 1.7290. Min Range: -1.7290

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1365573 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.7290. Min Act: -0.0000

Data Index: 648492 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.5263. Min Act: -0.0000

Data Index: 1059514 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.5197. Min Act: -0.0000

Data Index: 652712 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.4413. Min Act: -0.0000

Data Index: 697581 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.4614. Min Act: -0.0000

Data Index: 966892 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.4116. Min Act: -0.0000

Data Index: 1607718 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1256548 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.4622. Min Act: -0.0000

Data Index: 795791 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.5250. Min Act: -0.0000

Data Index: 792922 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.3262. Min Act: -0.0000

Data Index: 234928 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.2731. Min Act: -0.0000

Data Index: 823220 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1030363 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.2729. Min Act: -0.0000

Data Index: 715804 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.1922. Min Act: -0.0000

Data Index: 862435 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.2672. Min Act: 0.0000

Data Index: 1314283 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.1697. Min Act: -0.0000

Data Index: 557476 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.2667. Min Act: -0.0000

Data Index: 96453 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.2624. Min Act: -0.0000

Data Index: 666657 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 1.7290. Min Range: -1.7290

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1725336 (The Pile)

Max Activating Token Index: 959