< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 781 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: 2.6062. Min Range: -2.6062

Max Act: 2.6062. Min Act: -0.1700

Data Index: 1111764 (Open Web Text)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.5610. Min Act: -0.1700

Data Index: 6243759 (Open Web Text)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.5350. Min Act: -0.1700

Data Index: 1292064 (Open Web Text)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.5293. Min Act: -0.1700

Data Index: 2433767 (Open Web Text)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.5280. Min Act: -0.1700

Data Index: 1459326 (Open Web Text)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.5032. Min Act: -0.1700

Data Index: 7677047 (Open Web Text)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4865. Min Act: -0.1700

Data Index: 8740844 (Open Web Text)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4817. Min Act: -0.1700

Data Index: 3003774 (Open Web Text)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4809. Min Act: -0.1700

Data Index: 6280707 (Open Web Text)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4696. Min Act: -0.1700

Data Index: 1393053 (Open Web Text)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4719. Min Act: -0.1698

Data Index: 8318120 (Open Web Text)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4683. Min Act: -0.1700

Data Index: 6017188 (Open Web Text)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4345. Min Act: -0.1700

Data Index: 8826737 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4516. Min Act: -0.1696

Data Index: 3714505 (Open Web Text)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4497. Min Act: -0.1700

Data Index: 2464952 (Open Web Text)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4365. Min Act: -0.1699

Data Index: 8474227 (Open Web Text)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4439. Min Act: -0.1700

Data Index: 5544460 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4447. Min Act: -0.1700

Data Index: 61345 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4625. Min Act: -0.1700

Data Index: 2906798 (Open Web Text)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6062. Min Range: -2.6062

Max Act: 2.4308. Min Act: -0.1700

Data Index: 3298274 (Open Web Text)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #19