< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4055 in Layer 18

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.9873. Min Act: -0.1700

Data Index: 2000596 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.9561. Min Act: -0.1700

Data Index: 3013711 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.9404. Min Act: -0.1700

Data Index: 284425 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8779. Min Act: -0.1700

Data Index: 1794197 (The Pile)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8623. Min Act: -0.1700

Data Index: 8919561 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8623. Min Act: -0.1700

Data Index: 1834717 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8623. Min Act: -0.1700

Data Index: 10607864 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8466. Min Act: -0.1700

Data Index: 2978636 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8466. Min Act: -0.1700

Data Index: 6664128 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8466. Min Act: -0.1700

Data Index: 7134529 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8466. Min Act: -0.1700

Data Index: 624059 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8310. Min Act: -0.1700

Data Index: 6630582 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8310. Min Act: -0.1700

Data Index: 1299959 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.8310. Min Act: -0.1700

Data Index: 2450826 (The Pile)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.7841. Min Act: -0.1700

Data Index: 6382442 (The Pile)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.7841. Min Act: -0.1700

Data Index: 10591330 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.7841. Min Act: -0.1700

Data Index: 7222591 (The Pile)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.7684. Min Act: -0.1700

Data Index: 6308770 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.7528. Min Act: -0.1700

Data Index: 6916782 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9873. Min Range: -3.9873

Max Act: 3.7371. Min Act: -0.1700

Data Index: 5646717 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #19