< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 34 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.1444. Min Act: -0.1700

Data Index: 2127266 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.1444. Min Act: -0.1700

Data Index: 420798 (The Pile)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.1444. Min Act: -0.1700

Data Index: 3639324 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.1287. Min Act: -0.1700

Data Index: 1656126 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.1129. Min Act: -0.1700

Data Index: 10513577 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0971. Min Act: -0.1700

Data Index: 7301566 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0971. Min Act: -0.1700

Data Index: 4757506 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0971. Min Act: -0.1700

Data Index: 9041448 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0971. Min Act: -0.1700

Data Index: 3303997 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0814. Min Act: -0.1700

Data Index: 990394 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0656. Min Act: -0.1700

Data Index: 4052270 (The Pile)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0656. Min Act: -0.1700

Data Index: 5089356 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0656. Min Act: -0.1700

Data Index: 4713602 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0656. Min Act: -0.1700

Data Index: 5640756 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0656. Min Act: -0.1700

Data Index: 7215586 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0656. Min Act: -0.1700

Data Index: 4287458 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0656. Min Act: -0.1700

Data Index: 2273816 (The Pile)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0498. Min Act: -0.1700

Data Index: 3241625 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0498. Min Act: -0.1700

Data Index: 5189898 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1444. Min Range: -3.1444

Max Act: 3.0498. Min Act: -0.1700

Data Index: 7397176 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #19