< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2422 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: 2.9361. Min Range: -2.9361

Max Act: 2.9361. Min Act: -0.1157

Data Index: 583711 (Open Web Text)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.9259. Min Act: -0.1506

Data Index: 8679862 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8894. Min Act: -0.0955

Data Index: 583698 (Open Web Text)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8553. Min Act: -0.1691

Data Index: 3865983 (Open Web Text)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8651. Min Act: -0.1661

Data Index: 4876557 (Open Web Text)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8458. Min Act: -0.1395

Data Index: 2269661 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8442. Min Act: -0.1508

Data Index: 4079686 (Open Web Text)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8341. Min Act: -0.1669

Data Index: 5392497 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8315. Min Act: -0.1557

Data Index: 5915894 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8366. Min Act: -0.1312

Data Index: 5915893 (Open Web Text)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8283. Min Act: -0.1684

Data Index: 5937165 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8149. Min Act: -0.1696

Data Index: 4433193 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8043. Min Act: -0.1669

Data Index: 5395832 (Open Web Text)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.7909. Min Act: -0.1409

Data Index: 4500029 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.7936. Min Act: -0.1274

Data Index: 237836 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.7998. Min Act: -0.1378

Data Index: 1150068 (Open Web Text)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.7992. Min Act: -0.1029

Data Index: 74881 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.7916. Min Act: -0.1422

Data Index: 3455577 (Open Web Text)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.8079. Min Act: -0.1358

Data Index: 5631917 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9361. Min Range: -2.9361

Max Act: 2.7895. Min Act: -0.1700

Data Index: 59882 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #19