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

Dataset: The Pile

Neuron 3210 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9461. Min Act: -0.0000

Data Index: 466474 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1547364 (The Pile)

Max Activating Token Index: 547

Text #2

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1918315 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8288. Min Act: -0.0000

Data Index: 399772 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8063. Min Act: -0.0000

Data Index: 885687 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7807. Min Act: -0.0000

Data Index: 372623 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1429838 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7779. Min Act: -0.0000

Data Index: 999050 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1812762 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7350. Min Act: -0.0000

Data Index: 295391 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7398. Min Act: -0.0000

Data Index: 616721 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7114. Min Act: -0.0000

Data Index: 107144 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.6657. Min Act: -0.0000

Data Index: 42693 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1580281 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1081684 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1960867 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.6622. Min Act: -0.0000

Data Index: 577790 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.7012. Min Act: 0.0000

Data Index: 1604467 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.6524. Min Act: -0.0000

Data Index: 113522 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.6109. Min Act: -0.0000

Data Index: 180786 (The Pile)

Max Activating Token Index: 772