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

Dataset: The Pile

Neuron 3907 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: 3.9844. Min Range: -3.9844

Max Act: 3.9844. Min Act: -0.0000

Data Index: 1205064 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.8777. Min Act: -0.0000

Data Index: 1049133 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.3821. Min Act: -0.0000

Data Index: 777874 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.3740. Min Act: -0.0000

Data Index: 1263677 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.1884. Min Act: -0.0000

Data Index: 1416239 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.2675. Min Act: -0.0000

Data Index: 1926464 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.3553. Min Act: -0.0000

Data Index: 1675814 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.5938. Min Act: -0.0000

Data Index: 766088 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.1330. Min Act: -0.0000

Data Index: 1453742 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.2015. Min Act: -0.0000

Data Index: 1886568 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.3475. Min Act: -0.0000

Data Index: 1667747 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 3.9844. Min Range: -3.9844

Max Act: 2.9897. Min Act: -0.0000

Data Index: 209609 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 3.9844. Min Range: -3.9844

Max Act: 2.9918. Min Act: -0.0000

Data Index: 1499843 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 3.9844. Min Range: -3.9844

Max Act: 2.9809. Min Act: -0.0000

Data Index: 1646251 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.1370. Min Act: -0.0000

Data Index: 112716 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 3.9844. Min Range: -3.9844

Max Act: 2.9629. Min Act: -0.0000

Data Index: 427829 (The Pile)

Max Activating Token Index: 372

Text #16

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.1427. Min Act: -0.0000

Data Index: 1979769 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.3758. Min Act: -0.0000

Data Index: 1229696 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.1832. Min Act: -0.0000

Data Index: 772831 (The Pile)

Max Activating Token Index: 849

Text #19

Max Range: 3.9844. Min Range: -3.9844

Max Act: 3.0702. Min Act: -0.0000

Data Index: 1024904 (The Pile)

Max Activating Token Index: 303