< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4036 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.0696. Min Range: -3.0696

Max Act: 3.0696. Min Act: -0.1700

Data Index: 1690777 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0696. Min Range: -3.0696

Max Act: 3.0222. Min Act: -0.1700

Data Index: 5966362 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9906. Min Act: -0.1700

Data Index: 5872957 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9906. Min Act: -0.1700

Data Index: 7973193 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9748. Min Act: -0.1700

Data Index: 2047592 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9748. Min Act: -0.1700

Data Index: 7422770 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9748. Min Act: -0.1700

Data Index: 2668233 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9589. Min Act: -0.1700

Data Index: 552903 (The Pile)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9589. Min Act: -0.1700

Data Index: 5950711 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9431. Min Act: -0.1700

Data Index: 9453010 (The Pile)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9431. Min Act: -0.1700

Data Index: 8184433 (The Pile)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9431. Min Act: -0.1700

Data Index: 635287 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9431. Min Act: -0.1700

Data Index: 6741628 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9273. Min Act: -0.1700

Data Index: 4650102 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9273. Min Act: -0.1700

Data Index: 4293203 (The Pile)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9114. Min Act: -0.1700

Data Index: 5035636 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9114. Min Act: -0.1700

Data Index: 3413222 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9114. Min Act: -0.1700

Data Index: 6654489 (The Pile)

Max Activating Token Index: 966

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9114. Min Act: -0.1700

Data Index: 3433410 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0696. Min Range: -3.0696

Max Act: 2.9114. Min Act: -0.1700

Data Index: 1582530 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #19