< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 21 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.4706. Min Act: -0.1700

Data Index: 9324428 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.4219. Min Act: -0.1700

Data Index: 4573100 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.4056. Min Act: -0.1700

Data Index: 5983312 (The Pile)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.4056. Min Act: -0.1700

Data Index: 1727279 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.4056. Min Act: -0.1700

Data Index: 4613840 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3893. Min Act: -0.1700

Data Index: 10575693 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3893. Min Act: -0.1700

Data Index: 5770887 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3893. Min Act: -0.1700

Data Index: 4690619 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3893. Min Act: -0.1700

Data Index: 6710602 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3729. Min Act: -0.1700

Data Index: 8309131 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3729. Min Act: -0.1700

Data Index: 2358360 (The Pile)

Max Activating Token Index: 531

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3729. Min Act: -0.1700

Data Index: 2997133 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3729. Min Act: -0.1700

Data Index: 2994816 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3729. Min Act: -0.1700

Data Index: 9859059 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3566. Min Act: -0.1700

Data Index: 7936622 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3566. Min Act: -0.1700

Data Index: 7138896 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3566. Min Act: -0.1700

Data Index: 2440535 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3566. Min Act: -0.1700

Data Index: 1861329 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3402. Min Act: -0.1700

Data Index: 2283009 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.4706. Min Range: -2.4706

Max Act: 2.3402. Min Act: -0.1700

Data Index: 3501898 (The Pile)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #19