< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 26 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1001585 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1870722 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1938. Min Act: -0.0002

Data Index: 391149 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1835. Min Act: -0.0002

Data Index: 180818 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1876. Min Act: -0.0002

Data Index: 994604 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1867. Min Act: -0.0001

Data Index: 81663 (The Pile)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1118030 (The Pile)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1734. Min Act: -0.0001

Data Index: 1376477 (The Pile)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1722. Min Act: -0.0002

Data Index: 1364475 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1773. Min Act: -0.0001

Data Index: 1708171 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1747. Min Act: -0.0002

Data Index: 1155969 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1729. Min Act: -0.0002

Data Index: 1584200 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1787. Min Act: -0.0002

Data Index: 1175258 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1774. Min Act: -0.0002

Data Index: 1721870 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1698. Min Act: -0.0002

Data Index: 1053025 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1682. Min Act: -0.0002

Data Index: 521582 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1712. Min Act: -0.0002

Data Index: 1656192 (The Pile)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1650. Min Act: -0.0002

Data Index: 945951 (The Pile)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1039939 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2113. Min Range: -0.2113

Max Act: 0.1680. Min Act: -0.0002

Data Index: 1067538 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #19