< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 5112 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.7621. Min Act: -0.1700

Data Index: 975038 (Open Web Text)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.6839. Min Act: -0.1700

Data Index: 5042960 (Open Web Text)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.6526. Min Act: -0.1700

Data Index: 2075067 (Open Web Text)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.5431. Min Act: -0.1700

Data Index: 6194209 (Open Web Text)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.5117. Min Act: -0.1700

Data Index: 4468997 (Open Web Text)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4961. Min Act: -0.1700

Data Index: 7037360 (Open Web Text)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4961. Min Act: -0.1700

Data Index: 401281 (Open Web Text)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4647. Min Act: -0.1700

Data Index: 1442694 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4804. Min Act: -0.1700

Data Index: 4466206 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4804. Min Act: -0.1700

Data Index: 7396628 (Open Web Text)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4647. Min Act: -0.1700

Data Index: 1886894 (Open Web Text)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4491. Min Act: -0.1700

Data Index: 1513684 (Open Web Text)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4491. Min Act: -0.1700

Data Index: 7826344 (Open Web Text)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4491. Min Act: -0.1700

Data Index: 823307 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4334. Min Act: -0.1700

Data Index: 2605669 (Open Web Text)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4334. Min Act: -0.1700

Data Index: 2156605 (Open Web Text)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4334. Min Act: -0.1700

Data Index: 2977094 (Open Web Text)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4177. Min Act: -0.1700

Data Index: 2473118 (Open Web Text)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4177. Min Act: -0.1700

Data Index: 1802012 (Open Web Text)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7621. Min Range: -3.7621

Max Act: 3.4021. Min Act: -0.1700

Data Index: 5434711 (Open Web Text)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #19