< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3019 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.7231. Min Act: -0.0001

Data Index: 1765434 (The Pile)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6754. Min Act: -0.0001

Data Index: 1904263 (The Pile)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6603. Min Act: -0.0001

Data Index: 674783 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5848. Min Act: -0.0001

Data Index: 1685229 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5009. Min Act: -0.0001

Data Index: 1006681 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5185. Min Act: -0.0001

Data Index: 1553473 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4851. Min Act: -0.0001

Data Index: 1915565 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4702. Min Act: -0.0001

Data Index: 1242775 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5108. Min Act: -0.0001

Data Index: 633007 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5102. Min Act: -0.0001

Data Index: 570627 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4522. Min Act: -0.0001

Data Index: 1150545 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4876. Min Act: -0.0001

Data Index: 1480354 (The Pile)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5325. Min Act: -0.0001

Data Index: 802750 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4612. Min Act: -0.0001

Data Index: 774998 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3673. Min Act: -0.0001

Data Index: 1071124 (The Pile)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3985. Min Act: -0.0001

Data Index: 552191 (The Pile)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4016. Min Act: -0.0001

Data Index: 712326 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4359. Min Act: -0.0001

Data Index: 1640679 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4253. Min Act: -0.0001

Data Index: 224553 (The Pile)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5376. Min Act: -0.0001

Data Index: 1777600 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #19