< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6396 in Layer 36

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.7083. Min Act: -0.1700

Data Index: 3018387 (Open Web Text)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.6770. Min Act: -0.1700

Data Index: 1326791 (Open Web Text)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3958. Min Act: -0.1700

Data Index: 3095788 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3958. Min Act: -0.1700

Data Index: 1192378 (Open Web Text)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3645. Min Act: -0.1700

Data Index: 1574448 (Open Web Text)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3333. Min Act: -0.1700

Data Index: 1810704 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3020. Min Act: -0.1700

Data Index: 1395567 (Open Web Text)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3333. Min Act: -0.1700

Data Index: 4178491 (Open Web Text)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3020. Min Act: -0.1700

Data Index: 2974409 (Open Web Text)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2708. Min Act: -0.1700

Data Index: 138307 (Open Web Text)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2395. Min Act: -0.1700

Data Index: 6775552 (Open Web Text)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2395. Min Act: -0.1700

Data Index: 3270446 (Open Web Text)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2083. Min Act: -0.1700

Data Index: 1417876 (Open Web Text)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2083. Min Act: -0.1700

Data Index: 7399562 (Open Web Text)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2083. Min Act: -0.1700

Data Index: 2812641 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2083. Min Act: -0.1700

Data Index: 2631985 (Open Web Text)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2083. Min Act: -0.1700

Data Index: 7909321 (Open Web Text)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1770. Min Act: -0.1700

Data Index: 5067021 (Open Web Text)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1770. Min Act: -0.1700

Data Index: 6715544 (Open Web Text)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1770. Min Act: -0.1700

Data Index: 6715915 (Open Web Text)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #19