< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1789 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: 2.9373. Min Range: -2.9373

Max Act: 2.9373. Min Act: -0.1700

Data Index: 3736732 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.9205. Min Act: -0.1699

Data Index: 5272809 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8949. Min Act: -0.1700

Data Index: 3476666 (Open Web Text)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8770. Min Act: -0.1700

Data Index: 2067743 (Open Web Text)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8777. Min Act: -0.1700

Data Index: 7347069 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8452. Min Act: -0.1700

Data Index: 5398845 (Open Web Text)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8344. Min Act: -0.1700

Data Index: 6632516 (Open Web Text)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8362. Min Act: -0.1700

Data Index: 1041521 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8313. Min Act: -0.1700

Data Index: 2886784 (Open Web Text)

Max Activating Token Index: 710

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8350. Min Act: -0.1700

Data Index: 925860 (Open Web Text)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8206. Min Act: -0.1700

Data Index: 895195 (Open Web Text)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8242. Min Act: -0.1700

Data Index: 5176850 (Open Web Text)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.8031. Min Act: -0.1700

Data Index: 1597371 (Open Web Text)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.7851. Min Act: -0.1700

Data Index: 1330993 (Open Web Text)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.7880. Min Act: -0.1700

Data Index: 6595548 (Open Web Text)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.7945. Min Act: -0.1700

Data Index: 8704488 (Open Web Text)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.7888. Min Act: -0.1700

Data Index: 4636045 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.7827. Min Act: -0.1700

Data Index: 1153702 (Open Web Text)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.7677. Min Act: -0.1700

Data Index: 175737 (Open Web Text)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9373. Min Range: -2.9373

Max Act: 2.7879. Min Act: -0.1700

Data Index: 3398660 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #19