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

Dataset: The Pile

Neuron 4312 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.2807. Min Act: -0.0000

Data Index: 353939 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1045810 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.1377. Min Act: -0.0000

Data Index: 1255412 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9986. Min Act: -0.0000

Data Index: 429907 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.0346. Min Act: -0.0000

Data Index: 939627 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.6566. Min Act: -0.0000

Data Index: 174056 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1294495 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1044806 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9765. Min Act: -0.0000

Data Index: 273719 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9448. Min Act: -0.0000

Data Index: 957180 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9352. Min Act: -0.0000

Data Index: 557991 (The Pile)

Max Activating Token Index: 56

Text #11

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9280. Min Act: -0.0000

Data Index: 773879 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1772102 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9512. Min Act: -0.0000

Data Index: 29339 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9401. Min Act: -0.0000

Data Index: 483094 (The Pile)

Max Activating Token Index: 684

Text #15

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1623258 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.8358. Min Act: -0.0000

Data Index: 413083 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1279584 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.8684. Min Act: -0.0000

Data Index: 642841 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.8643. Min Act: -0.0000

Data Index: 157586 (The Pile)

Max Activating Token Index: 131