< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2779 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: 2.8382. Min Range: -2.8382

Max Act: 2.8382. Min Act: -0.1700

Data Index: 6358999 (Open Web Text)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.7191. Min Act: -0.1700

Data Index: 2728087 (Open Web Text)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.6560. Min Act: -0.1700

Data Index: 2868302 (Open Web Text)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5886. Min Act: -0.1700

Data Index: 544104 (Open Web Text)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.6151. Min Act: -0.1700

Data Index: 8222197 (Open Web Text)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5874. Min Act: -0.1700

Data Index: 4607450 (Open Web Text)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5895. Min Act: -0.1700

Data Index: 1285309 (Open Web Text)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.6049. Min Act: -0.1700

Data Index: 7066354 (Open Web Text)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5875. Min Act: -0.1700

Data Index: 2430261 (Open Web Text)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5859. Min Act: -0.1700

Data Index: 1196106 (Open Web Text)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5916. Min Act: -0.1700

Data Index: 255632 (Open Web Text)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5289. Min Act: -0.1700

Data Index: 7641451 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5502. Min Act: -0.1700

Data Index: 5290140 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5372. Min Act: -0.1700

Data Index: 8558415 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5268. Min Act: -0.1700

Data Index: 2976939 (Open Web Text)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5512. Min Act: -0.1700

Data Index: 3867220 (Open Web Text)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5329. Min Act: -0.1700

Data Index: 1510278 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5078. Min Act: -0.1700

Data Index: 7687522 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5304. Min Act: -0.1700

Data Index: 3912704 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8382. Min Range: -2.8382

Max Act: 2.5270. Min Act: -0.1700

Data Index: 1872817 (Open Web Text)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #19