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

Dataset: The Pile

Neuron 3500 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: 0.4700. Min Range: -0.4700

Max Act: 0.4700. Min Act: -0.0000

Data Index: 186233 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1785905 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1250145 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1081126 (The Pile)

Max Activating Token Index: 689

Text #4

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1140398 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1422757 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3732. Min Act: -0.0000

Data Index: 293685 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3572. Min Act: -0.0000

Data Index: 626423 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3995. Min Act: -0.0000

Data Index: 480313 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3801. Min Act: -0.0000

Data Index: 286034 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3623. Min Act: -0.0000

Data Index: 120398 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3793. Min Act: -0.0000

Data Index: 348662 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3857. Min Act: -0.0000

Data Index: 959012 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3801. Min Act: -0.0000

Data Index: 61213 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3738. Min Act: -0.0000

Data Index: 586761 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3508. Min Act: -0.0000

Data Index: 482567 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3824. Min Act: -0.0000

Data Index: 215427 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3579. Min Act: -0.0000

Data Index: 916217 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3690. Min Act: -0.0000

Data Index: 427642 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1218190 (The Pile)

Max Activating Token Index: 846