< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1553 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.6938. Min Act: -0.1700

Data Index: 7602795 (Open Web Text)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.6702. Min Act: -0.1700

Data Index: 7310923 (Open Web Text)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.6385. Min Act: -0.1700

Data Index: 7371646 (Open Web Text)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.6076. Min Act: -0.1700

Data Index: 6766203 (Open Web Text)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.6180. Min Act: -0.1700

Data Index: 4122522 (Open Web Text)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5797. Min Act: -0.1700

Data Index: 7946253 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5704. Min Act: -0.1700

Data Index: 8258103 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5825. Min Act: -0.1700

Data Index: 7032318 (Open Web Text)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5530. Min Act: -0.1700

Data Index: 5463087 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5602. Min Act: -0.1700

Data Index: 5421351 (Open Web Text)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5606. Min Act: -0.1700

Data Index: 6307659 (Open Web Text)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5545. Min Act: -0.1700

Data Index: 7424615 (Open Web Text)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5455. Min Act: -0.1700

Data Index: 6327837 (Open Web Text)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5339. Min Act: -0.1700

Data Index: 3590255 (Open Web Text)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5277. Min Act: -0.1700

Data Index: 3039390 (Open Web Text)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5383. Min Act: -0.1700

Data Index: 7264692 (Open Web Text)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5420. Min Act: -0.1700

Data Index: 22726 (Open Web Text)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5334. Min Act: -0.1700

Data Index: 4938870 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5435. Min Act: -0.1700

Data Index: 3455973 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6938. Min Range: -2.6938

Max Act: 2.5297. Min Act: -0.1700

Data Index: 6907975 (Open Web Text)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #19