< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1980 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.5751. Min Act: -0.1424

Data Index: 9496467 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.8412. Min Act: -0.1666

Data Index: 8320105 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.7473. Min Act: -0.1670

Data Index: 6028666 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.8724. Min Act: -0.1700

Data Index: 4919864 (The Pile)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.6534. Min Act: -0.1340

Data Index: 9998009 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.5751. Min Act: -0.1700

Data Index: 2269090 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.9037. Min Act: -0.1700

Data Index: 4873014 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.3714. Min Act: -0.1567

Data Index: 8701991 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.4968. Min Act: -0.1654

Data Index: 2760566 (The Pile)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.5125. Min Act: -0.1693

Data Index: 1597008 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.7160. Min Act: -0.1506

Data Index: 1320540 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.7160. Min Act: -0.1691

Data Index: 9007861 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.4341. Min Act: -0.1700

Data Index: 8185441 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.3557. Min Act: -0.1198

Data Index: 5992607 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.8099. Min Act: -0.1690

Data Index: 409285 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.7160. Min Act: -0.1699

Data Index: 3257299 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.4655. Min Act: -0.1679

Data Index: 1242618 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.3400. Min Act: -0.1699

Data Index: 6411214 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.6378. Min Act: -0.1696

Data Index: 8702232 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9037. Min Range: -3.9037

Max Act: 3.4341. Min Act: -0.1462

Data Index: 7207922 (The Pile)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #19