< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 596 in Layer 4

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: 2.9481. Min Range: -2.9481

Max Act: 2.9481. Min Act: -0.1700

Data Index: 6977497 (Open Web Text)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.8923. Min Act: -0.1700

Data Index: 4398937 (Open Web Text)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.8973. Min Act: -0.1700

Data Index: 3507271 (Open Web Text)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.8948. Min Act: -0.1700

Data Index: 1934876 (Open Web Text)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.8398. Min Act: -0.1700

Data Index: 6719845 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.8700. Min Act: -0.1700

Data Index: 4170010 (Open Web Text)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.8185. Min Act: -0.1700

Data Index: 5524641 (Open Web Text)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.8223. Min Act: -0.1700

Data Index: 6994832 (Open Web Text)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7860. Min Act: -0.1700

Data Index: 7623489 (Open Web Text)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7658. Min Act: -0.1700

Data Index: 2738932 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.8087. Min Act: -0.1700

Data Index: 3313037 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7770. Min Act: -0.1700

Data Index: 6266330 (Open Web Text)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7723. Min Act: -0.1700

Data Index: 7099093 (Open Web Text)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7658. Min Act: -0.1700

Data Index: 4898216 (Open Web Text)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7638. Min Act: -0.1700

Data Index: 2478366 (Open Web Text)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7539. Min Act: -0.1700

Data Index: 5880974 (Open Web Text)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7602. Min Act: -0.1700

Data Index: 3671889 (Open Web Text)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7561. Min Act: -0.1700

Data Index: 637204 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7401. Min Act: -0.1700

Data Index: 5889385 (Open Web Text)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9481. Min Range: -2.9481

Max Act: 2.7427. Min Act: -0.1700

Data Index: 1684984 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #19