< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1023 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: 2.5614. Min Range: -2.5614

Max Act: 2.5614. Min Act: -0.1700

Data Index: 6156684 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.5614. Min Act: -0.1700

Data Index: 10268646 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.5453. Min Act: -0.1700

Data Index: 10192591 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4806. Min Act: -0.1700

Data Index: 4438681 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.5130. Min Act: -0.1700

Data Index: 3481365 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4968. Min Act: -0.1700

Data Index: 5395935 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4968. Min Act: -0.1700

Data Index: 2061932 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4481. Min Act: -0.1700

Data Index: 10481735 (The Pile)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4968. Min Act: -0.1700

Data Index: 5106066 (The Pile)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4644. Min Act: -0.1700

Data Index: 8923090 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4644. Min Act: -0.1700

Data Index: 9019957 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4806. Min Act: -0.1700

Data Index: 7402074 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4968. Min Act: -0.1700

Data Index: 5251267 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4806. Min Act: -0.1700

Data Index: 2119760 (The Pile)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4806. Min Act: -0.1700

Data Index: 4943730 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4806. Min Act: -0.1700

Data Index: 7152338 (The Pile)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4644. Min Act: -0.1700

Data Index: 8451758 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4562. Min Act: -0.1700

Data Index: 4644306 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4806. Min Act: -0.1700

Data Index: 4684976 (The Pile)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5614. Min Range: -2.5614

Max Act: 2.4481. Min Act: -0.1700

Data Index: 5284650 (The Pile)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #19