< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2304 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.1627. Min Act: -0.0002

Data Index: 1055007 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.1424. Min Act: -0.0002

Data Index: 1084662 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0629. Min Act: -0.0002

Data Index: 743163 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0368. Min Act: -0.0002

Data Index: 1180779 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0368. Min Act: -0.0002

Data Index: 1789462 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0542. Min Act: -0.0002

Data Index: 1439482 (The Pile)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0127. Min Act: -0.0002

Data Index: 1415143 (The Pile)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0432. Min Act: -0.0002

Data Index: 1483828 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0331. Min Act: -0.0002

Data Index: 1772384 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0065. Min Act: -0.0002

Data Index: 1299457 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9933. Min Act: -0.0002

Data Index: 325810 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9916. Min Act: -0.0002

Data Index: 1387729 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0247. Min Act: -0.0002

Data Index: 1097092 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9833. Min Act: -0.0002

Data Index: 1688853 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9885. Min Act: -0.0002

Data Index: 999404 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0109. Min Act: -0.0002

Data Index: 1337994 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0092. Min Act: -0.0002

Data Index: 1888321 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9990. Min Act: -0.0002

Data Index: 1142507 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9743. Min Act: -0.0002

Data Index: 602762 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9951. Min Act: -0.0002

Data Index: 573954 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #19