< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 26 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.6810. Min Act: -0.0000

Data Index: 778570 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5461. Min Act: -0.0000

Data Index: 585935 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1637778 (The Pile)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5290. Min Act: -0.0000

Data Index: 421630 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5088. Min Act: -0.0000

Data Index: 289279 (The Pile)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5046. Min Act: -0.0000

Data Index: 241671 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1627345 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1865843 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1785072 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1538962 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1902554 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1387989 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4430. Min Act: -0.0000

Data Index: 321522 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4412. Min Act: -0.0000

Data Index: 867763 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1480728 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1038779 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1380310 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4583. Min Act: -0.0000

Data Index: 848628 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1560442 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6810. Min Range: -0.6810

Max Act: 0.4197. Min Act: -0.0000

Data Index: 914066 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #19