< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2959 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: 4.8608. Min Range: -4.8608

Max Act: 4.8608. Min Act: -0.1700

Data Index: 4556999 (Open Web Text)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.8356. Min Act: -0.1700

Data Index: 3847529 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.8571. Min Act: -0.1700

Data Index: 2472829 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7802. Min Act: -0.1700

Data Index: 7622999 (Open Web Text)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7793. Min Act: -0.1700

Data Index: 5258582 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7823. Min Act: -0.1700

Data Index: 8710971 (Open Web Text)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7472. Min Act: -0.1700

Data Index: 4774715 (Open Web Text)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7036. Min Act: -0.1700

Data Index: 862650 (Open Web Text)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7292. Min Act: -0.1700

Data Index: 3299888 (Open Web Text)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7195. Min Act: -0.1700

Data Index: 1333487 (Open Web Text)

Max Activating Token Index: 461

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7267. Min Act: -0.1700

Data Index: 8147116 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7516. Min Act: -0.1700

Data Index: 2036922 (Open Web Text)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.7311. Min Act: -0.1700

Data Index: 7976558 (Open Web Text)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.6966. Min Act: -0.1700

Data Index: 802545 (Open Web Text)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.6844. Min Act: -0.1700

Data Index: 5150330 (Open Web Text)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.6624. Min Act: -0.1700

Data Index: 894167 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.6984. Min Act: -0.1700

Data Index: 6333228 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.6578. Min Act: -0.1700

Data Index: 6031091 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.6603. Min Act: -0.1700

Data Index: 6095673 (Open Web Text)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.8608. Min Range: -4.8608

Max Act: 4.6751. Min Act: -0.1700

Data Index: 316669 (Open Web Text)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #19