< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2839 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: 2.8716. Min Range: -2.8716

Max Act: 2.8716. Min Act: -0.1700

Data Index: 5033583 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.8375. Min Act: -0.1700

Data Index: 6200287 (Open Web Text)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.8259. Min Act: -0.1700

Data Index: 2457729 (Open Web Text)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.8225. Min Act: -0.1700

Data Index: 2556676 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.8175. Min Act: -0.1700

Data Index: 6703360 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7947. Min Act: -0.1700

Data Index: 2440324 (Open Web Text)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7901. Min Act: -0.1700

Data Index: 5066695 (Open Web Text)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7716. Min Act: -0.1700

Data Index: 2847197 (Open Web Text)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7711. Min Act: -0.1700

Data Index: 3083339 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7470. Min Act: -0.1700

Data Index: 1463847 (Open Web Text)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7623. Min Act: -0.1700

Data Index: 3421513 (Open Web Text)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7169. Min Act: -0.1700

Data Index: 91097 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7298. Min Act: -0.1700

Data Index: 2724927 (Open Web Text)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7331. Min Act: -0.1700

Data Index: 1989906 (Open Web Text)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.6850. Min Act: -0.1700

Data Index: 577271 (Open Web Text)

Max Activating Token Index: 999

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.6962. Min Act: -0.1700

Data Index: 6448664 (Open Web Text)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7048. Min Act: -0.1700

Data Index: 7343622 (Open Web Text)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.7029. Min Act: -0.1700

Data Index: 182094 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.6798. Min Act: -0.1700

Data Index: 1285600 (Open Web Text)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8716. Min Range: -2.8716

Max Act: 2.6829. Min Act: -0.1700

Data Index: 4416134 (Open Web Text)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #19