< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 32 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.4645. Min Act: -0.1602

Data Index: 811562 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.4020. Min Act: -0.1691

Data Index: 5366968 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.3395. Min Act: -0.1699

Data Index: 7112985 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2770. Min Act: -0.1699

Data Index: 3639815 (The Pile)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2770. Min Act: -0.1700

Data Index: 1659091 (The Pile)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2770. Min Act: -0.1698

Data Index: 1311058 (The Pile)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2770. Min Act: -0.1699

Data Index: 7857684 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2770. Min Act: -0.1699

Data Index: 3714509 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2770. Min Act: -0.1400

Data Index: 944035 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2145. Min Act: -0.1693

Data Index: 6845912 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2145. Min Act: -0.1700

Data Index: 6779248 (The Pile)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2145. Min Act: -0.1651

Data Index: 3510654 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2145. Min Act: -0.1699

Data Index: 10564340 (The Pile)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2145. Min Act: -0.1695

Data Index: 320541 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.2145. Min Act: -0.1700

Data Index: 7386001 (The Pile)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.1520. Min Act: -0.1691

Data Index: 4232066 (The Pile)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.1520. Min Act: -0.0853

Data Index: 5863080 (The Pile)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.1520. Min Act: -0.1699

Data Index: 6639605 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.1520. Min Act: -0.1700

Data Index: 2790136 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 8.4645. Min Range: -8.4645

Max Act: 8.1520. Min Act: -0.1399

Data Index: 4284145 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #19