< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 11 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.1363. Min Range: -6.1363

Max Act: 6.1363. Min Act: -0.1426

Data Index: 7183934 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.1363. Min Range: -6.1363

Max Act: 6.0738. Min Act: -0.1426

Data Index: 1073140 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.7301. Min Act: -0.1426

Data Index: 8922939 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.6363. Min Act: -0.1699

Data Index: 2304047 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.1832. Min Act: -0.1426

Data Index: 8422332 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.1832. Min Act: -0.1426

Data Index: 10301090 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 73125 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 4436181 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 4153405 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 8298677 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 3525983 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 3760748 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 6171966 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 2154935 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 3181284 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 8168335 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0426. Min Act: -0.1426

Data Index: 4147146 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0113. Min Act: -0.1426

Data Index: 5257990 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.1363. Min Range: -6.1363

Max Act: 5.0113. Min Act: -0.1426

Data Index: 6048225 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.1363. Min Range: -6.1363

Max Act: 4.9488. Min Act: -0.1687

Data Index: 2804357 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #19