< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 28 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.4112. Min Act: -0.0001

Data Index: 23903 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.1456. Min Act: -0.0001

Data Index: 203688 (The Pile)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.2243. Min Act: -0.0001

Data Index: 125860 (The Pile)

Max Activating Token Index: 296

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.1631. Min Act: -0.0001

Data Index: 273581 (The Pile)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.0179. Min Act: -0.0001

Data Index: 1181931 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.0129. Min Act: -0.0001

Data Index: 1938739 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.8702. Min Act: -0.0001

Data Index: 1090111 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4112. Min Range: -3.4112

Max Act: 3.0190. Min Act: -0.0001

Data Index: 1084023 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.9877. Min Act: -0.0001

Data Index: 518538 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.8927. Min Act: -0.0001

Data Index: 270472 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.8731. Min Act: -0.0001

Data Index: 536021 (The Pile)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.8677. Min Act: -0.0001

Data Index: 1482755 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.7759. Min Act: -0.0001

Data Index: 1055433 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.6747. Min Act: -0.0001

Data Index: 1397596 (The Pile)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.8281. Min Act: -0.0001

Data Index: 733586 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.8770. Min Act: -0.0001

Data Index: 570976 (The Pile)

Max Activating Token Index: 531

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.7495. Min Act: -0.0001

Data Index: 689802 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.9935. Min Act: -0.0001

Data Index: 1224786 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.9419. Min Act: -0.0001

Data Index: 1933679 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4112. Min Range: -3.4112

Max Act: 2.7844. Min Act: -0.0001

Data Index: 903041 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #19