< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 28 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: 4.8991. Min Range: -4.8991

Max Act: 4.8991. Min Act: -0.1700

Data Index: 6578260 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.6491. Min Act: -0.1700

Data Index: 3359024 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.5241. Min Act: -0.1700

Data Index: 10337251 (The Pile)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.4928. Min Act: -0.1700

Data Index: 1433608 (The Pile)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.4616. Min Act: -0.1700

Data Index: 7558443 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.4303. Min Act: -0.1700

Data Index: 675085 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.4303. Min Act: -0.1700

Data Index: 603094 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.4303. Min Act: -0.1700

Data Index: 7453623 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.3990. Min Act: -0.1700

Data Index: 6351721 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.3990. Min Act: -0.1700

Data Index: 6254654 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.3365. Min Act: -0.1700

Data Index: 2971178 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.3365. Min Act: -0.1700

Data Index: 9735735 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.3365. Min Act: -0.1700

Data Index: 9211162 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.3053. Min Act: -0.1700

Data Index: 9256120 (The Pile)

Max Activating Token Index: 845

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.3053. Min Act: -0.1700

Data Index: 7822853 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.3053. Min Act: -0.1700

Data Index: 2915921 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.2740. Min Act: -0.1700

Data Index: 7142790 (The Pile)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.2740. Min Act: -0.1700

Data Index: 3891972 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.2740. Min Act: -0.1700

Data Index: 5190550 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8991. Min Range: -4.8991

Max Act: 4.2428. Min Act: -0.1700

Data Index: 5351872 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #19