< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2025 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.4655. Min Act: -0.1700

Data Index: 9949929 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.3557. Min Act: -0.1700

Data Index: 1948014 (The Pile)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.3243. Min Act: -0.1700

Data Index: 5165931 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.3557. Min Act: -0.1700

Data Index: 10089915 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.2301. Min Act: -0.1700

Data Index: 250208 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.2301. Min Act: -0.1700

Data Index: 9293958 (The Pile)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1671. Min Act: -0.1700

Data Index: 2210520 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1671. Min Act: -0.1700

Data Index: 6474447 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.0410. Min Act: -0.1700

Data Index: 4820950 (The Pile)

Max Activating Token Index: 932

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1514. Min Act: -0.1700

Data Index: 6966978 (The Pile)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1356. Min Act: -0.1700

Data Index: 9852963 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.2301. Min Act: -0.1699

Data Index: 10004235 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1829. Min Act: -0.1700

Data Index: 2239406 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.2458. Min Act: -0.1700

Data Index: 8615410 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.2143. Min Act: -0.1700

Data Index: 1289289 (The Pile)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1986. Min Act: -0.1700

Data Index: 3468589 (The Pile)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1041. Min Act: -0.1700

Data Index: 7669808 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.0094. Min Act: -0.1700

Data Index: 9644373 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1986. Min Act: -0.1700

Data Index: 9274677 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4655. Min Range: -3.4655

Max Act: 3.1356. Min Act: -0.1700

Data Index: 2151351 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #19