< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4075 in Layer 14

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.1296. Min Act: -0.1700

Data Index: 2682980 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.0823. Min Act: -0.1700

Data Index: 8658190 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.0823. Min Act: -0.1700

Data Index: 6515380 (The Pile)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.0665. Min Act: -0.1700

Data Index: 3951779 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.0350. Min Act: -0.1700

Data Index: 5232114 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.0350. Min Act: -0.1700

Data Index: 4626316 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.0350. Min Act: -0.1700

Data Index: 2556552 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.0350. Min Act: -0.1700

Data Index: 9783146 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1296. Min Range: -3.1296

Max Act: 3.0192. Min Act: -0.1700

Data Index: 2088598 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9875. Min Act: -0.1700

Data Index: 2341381 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9875. Min Act: -0.1700

Data Index: 4379568 (The Pile)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9875. Min Act: -0.1700

Data Index: 7477778 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9875. Min Act: -0.1700

Data Index: 9656462 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9875. Min Act: -0.1700

Data Index: 4760594 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9875. Min Act: -0.1700

Data Index: 1243922 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9717. Min Act: -0.1700

Data Index: 6154496 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9559. Min Act: -0.1700

Data Index: 2551967 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9559. Min Act: -0.1700

Data Index: 809486 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9559. Min Act: -0.1700

Data Index: 5029627 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1296. Min Range: -3.1296

Max Act: 2.9401. Min Act: -0.1700

Data Index: 4324906 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #19