< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 25 in Layer 16

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.2867. Min Range: -5.2867

Max Act: 5.2867. Min Act: -0.1700

Data Index: 1850029 (Open Web Text)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.2867. Min Range: -5.2867

Max Act: 5.2867. Min Act: -0.1700

Data Index: 7017595 (Open Web Text)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.2867. Min Range: -5.2867

Max Act: 5.2242. Min Act: -0.1700

Data Index: 6126378 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.2867. Min Range: -5.2867

Max Act: 5.0680. Min Act: -0.1700

Data Index: 5749201 (Open Web Text)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.9742. Min Act: -0.1700

Data Index: 6509776 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.2867. Min Range: -5.2867

Max Act: 5.0055. Min Act: -0.1700

Data Index: 8584806 (Open Web Text)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.2867. Min Range: -5.2867

Max Act: 5.0055. Min Act: -0.1700

Data Index: 2604601 (Open Web Text)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.2867. Min Range: -5.2867

Max Act: 5.0055. Min Act: -0.1700

Data Index: 72850 (Open Web Text)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.9742. Min Act: -0.1700

Data Index: 3997675 (Open Web Text)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.9742. Min Act: -0.1700

Data Index: 4947433 (Open Web Text)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.9742. Min Act: -0.1700

Data Index: 4671337 (Open Web Text)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.9430. Min Act: -0.1700

Data Index: 7978388 (Open Web Text)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.9430. Min Act: -0.1700

Data Index: 5048547 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.9117. Min Act: -0.1700

Data Index: 3792764 (Open Web Text)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.8805. Min Act: -0.1700

Data Index: 3627747 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.9117. Min Act: -0.1700

Data Index: 6981649 (Open Web Text)

Max Activating Token Index: 967

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.8492. Min Act: -0.1700

Data Index: 7618320 (Open Web Text)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.8805. Min Act: -0.1700

Data Index: 5517837 (Open Web Text)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.8805. Min Act: -0.1700

Data Index: 2681017 (Open Web Text)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.2867. Min Range: -5.2867

Max Act: 4.8805. Min Act: -0.1700

Data Index: 4455778 (Open Web Text)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #19