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

Dataset: The Pile

Neuron 3370 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3710. Min Act: -0.0000

Data Index: 106657 (The Pile)

Max Activating Token Index: 311

Text #1

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1706462 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3438. Min Act: -0.0000

Data Index: 105854 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3464. Min Act: -0.0000

Data Index: 506464 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1711767 (The Pile)

Max Activating Token Index: 616

Text #5

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1148628 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1412577 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2838. Min Act: -0.0000

Data Index: 932484 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2871. Min Act: -0.0000

Data Index: 311143 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.3313. Min Act: -0.0000

Data Index: 453836 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2916. Min Act: -0.0000

Data Index: 713544 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1901171 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2811. Min Act: -0.0000

Data Index: 879902 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1671799 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2725. Min Act: -0.0000

Data Index: 474855 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2869. Min Act: -0.0000

Data Index: 660683 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2663. Min Act: -0.0000

Data Index: 994914 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2949. Min Act: -0.0000

Data Index: 61642 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1843870 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 0.3733. Min Range: -0.3733

Max Act: 0.2617. Min Act: -0.0000

Data Index: 158212 (The Pile)

Max Activating Token Index: 404