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

Dataset: The Pile

Neuron 1941 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: 0.9108. Min Range: -0.9108

Max Act: 0.9028. Min Act: -0.0000

Data Index: 788062 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7689. Min Act: -0.0000

Data Index: 905561 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.8413. Min Act: -0.0000

Data Index: 818744 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.9108. Min Act: -0.0000

Data Index: 509246 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1962627 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.8655. Min Act: -0.0000

Data Index: 924156 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1389904 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7531. Min Act: -0.0000

Data Index: 481973 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.8534. Min Act: -0.0000

Data Index: 937816 (The Pile)

Max Activating Token Index: 485

Text #9

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1803226 (The Pile)

Max Activating Token Index: 750

Text #10

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7976. Min Act: -0.0000

Data Index: 85524 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1592682 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6690. Min Act: -0.0000

Data Index: 352755 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6933. Min Act: -0.0000

Data Index: 813660 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7486. Min Act: -0.0000

Data Index: 255151 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7319. Min Act: -0.0000

Data Index: 6558 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1538515 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1347989 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.8000. Min Act: -0.0000

Data Index: 510421 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7299. Min Act: -0.0000

Data Index: 515519 (The Pile)

Max Activating Token Index: 570