< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 427 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: 2.1180. Min Range: -2.1180

Max Act: 2.1180. Min Act: -0.1700

Data Index: 922591 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0826. Min Act: -0.1700

Data Index: 8230749 (Open Web Text)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0911. Min Act: -0.1700

Data Index: 2902291 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0503. Min Act: -0.1700

Data Index: 4771679 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0494. Min Act: -0.1700

Data Index: 5494210 (Open Web Text)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0809. Min Act: -0.1700

Data Index: 6351816 (Open Web Text)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0731. Min Act: -0.1700

Data Index: 8086976 (Open Web Text)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0236. Min Act: -0.1700

Data Index: 2768671 (Open Web Text)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0284. Min Act: -0.1700

Data Index: 3050113 (Open Web Text)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0521. Min Act: -0.1700

Data Index: 773089 (Open Web Text)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0320. Min Act: -0.1700

Data Index: 616261 (Open Web Text)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0240. Min Act: -0.1700

Data Index: 3479040 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0390. Min Act: -0.1700

Data Index: 5988638 (Open Web Text)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0220. Min Act: -0.1700

Data Index: 3608058 (Open Web Text)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0142. Min Act: -0.1700

Data Index: 7129389 (Open Web Text)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0109. Min Act: -0.1700

Data Index: 3197526 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0052. Min Act: -0.1700

Data Index: 5477668 (Open Web Text)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0098. Min Act: -0.1700

Data Index: 4988819 (Open Web Text)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1180. Min Range: -2.1180

Max Act: 1.9956. Min Act: -0.1700

Data Index: 1197292 (Open Web Text)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1180. Min Range: -2.1180

Max Act: 2.0076. Min Act: -0.1700

Data Index: 1800550 (Open Web Text)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #19