< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1510 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.9884. Min Act: -0.1700

Data Index: 434516 (Open Web Text)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.9978. Min Act: -0.1700

Data Index: 5433527 (Open Web Text)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.9063. Min Act: -0.1700

Data Index: 2957492 (Open Web Text)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8828. Min Act: -0.1700

Data Index: 5340801 (Open Web Text)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8881. Min Act: -0.1700

Data Index: 6754539 (Open Web Text)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8746. Min Act: -0.1700

Data Index: 5720167 (Open Web Text)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8450. Min Act: -0.1700

Data Index: 3464100 (Open Web Text)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8635. Min Act: -0.1700

Data Index: 5992860 (Open Web Text)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8477. Min Act: -0.1700

Data Index: 1270247 (Open Web Text)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8373. Min Act: -0.1700

Data Index: 1639736 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8430. Min Act: -0.1700

Data Index: 4690399 (Open Web Text)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8375. Min Act: -0.1700

Data Index: 6212351 (Open Web Text)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8455. Min Act: -0.1700

Data Index: 3900174 (Open Web Text)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8394. Min Act: -0.1700

Data Index: 381846 (Open Web Text)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8330. Min Act: -0.1700

Data Index: 7290272 (Open Web Text)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8261. Min Act: -0.1700

Data Index: 7448335 (Open Web Text)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8137. Min Act: -0.1700

Data Index: 2404801 (Open Web Text)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8033. Min Act: -0.1700

Data Index: 7976819 (Open Web Text)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.8128. Min Act: -0.1700

Data Index: 1960635 (Open Web Text)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9978. Min Range: -2.9978

Max Act: 2.7793. Min Act: -0.1700

Data Index: 46045 (Open Web Text)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #19