< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 20 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0003

Data Index: 1108871 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1322267 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0751. Min Act: -0.0003

Data Index: 772866 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0736. Min Act: -0.0003

Data Index: 107600 (The Pile)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0750. Min Act: -0.0003

Data Index: 493904 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1467241 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1904780 (The Pile)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1154400 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0707. Min Act: -0.0003

Data Index: 1952197 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1993089 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0691. Min Act: -0.0003

Data Index: 458466 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1322456 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0707. Min Act: -0.0003

Data Index: 555184 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1510067 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1770817 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0669. Min Act: -0.0003

Data Index: 797266 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1379114 (The Pile)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0697. Min Act: -0.0003

Data Index: 590130 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1873412 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1266992 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #19