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

Dataset: The Pile

Neuron 3866 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: 0.6045. Min Range: -0.6045

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1215042 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1640847 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3947. Min Act: -0.0000

Data Index: 675835 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1535525 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3681. Min Act: -0.0000

Data Index: 463355 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3379. Min Act: -0.0000

Data Index: 397787 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1100694 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1014592 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1929055 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3729. Min Act: -0.0000

Data Index: 386564 (The Pile)

Max Activating Token Index: 195

Text #10

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1418856 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1285810 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1813473 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3434. Min Act: -0.0000

Data Index: 165240 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3538. Min Act: -0.0000

Data Index: 398016 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1583930 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3501. Min Act: -0.0000

Data Index: 477479 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1886981 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1805149 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1067235 (The Pile)

Max Activating Token Index: 246