< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2029 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.2284. Min Act: -0.1700

Data Index: 10425171 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.1034. Min Act: -0.1700

Data Index: 2431915 (The Pile)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.1972. Min Act: -0.1700

Data Index: 10252180 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.0722. Min Act: -0.1699

Data Index: 9953043 (The Pile)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.6972. Min Act: -0.1700

Data Index: 6853091 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.1972. Min Act: -0.1700

Data Index: 6110570 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.0722. Min Act: -0.1700

Data Index: 4566890 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.1034. Min Act: -0.1700

Data Index: 3720367 (The Pile)

Max Activating Token Index: 968

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.1034. Min Act: -0.1700

Data Index: 2566322 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.0409. Min Act: -0.1700

Data Index: 1542317 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.2284. Min Range: -7.2284

Max Act: 7.0409. Min Act: -0.1700

Data Index: 2195188 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.9159. Min Act: -0.1699

Data Index: 10231774 (The Pile)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.5722. Min Act: -0.1700

Data Index: 10040896 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.9472. Min Act: -0.1700

Data Index: 4273562 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.9472. Min Act: -0.1700

Data Index: 7353166 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.9784. Min Act: -0.1700

Data Index: 10555672 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.9472. Min Act: -0.1700

Data Index: 6420186 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.9472. Min Act: -0.1700

Data Index: 3049225 (The Pile)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.7597. Min Act: -0.1699

Data Index: 1012736 (The Pile)

Max Activating Token Index: 838

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.2284. Min Range: -7.2284

Max Act: 6.8847. Min Act: -0.1700

Data Index: 1496575 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #19