< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2402 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: 4.7146. Min Range: -4.7146

Max Act: 4.7146. Min Act: -0.1364

Data Index: 8300616 (Open Web Text)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.6524. Min Act: -0.1690

Data Index: 8658481 (Open Web Text)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.5874. Min Act: -0.1097

Data Index: 7001790 (Open Web Text)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.6101. Min Act: -0.1694

Data Index: 4164438 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.5443. Min Act: -0.0076

Data Index: 7007083 (Open Web Text)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.5761. Min Act: -0.1182

Data Index: 3602316 (Open Web Text)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.5227. Min Act: -0.1639

Data Index: 1845408 (Open Web Text)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.5203. Min Act: -0.1608

Data Index: 118489 (Open Web Text)

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4761. Min Act: -0.1598

Data Index: 8439566 (Open Web Text)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.5096. Min Act: -0.1572

Data Index: 5566639 (Open Web Text)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.5003. Min Act: -0.1658

Data Index: 6996241 (Open Web Text)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4983. Min Act: -0.1536

Data Index: 2903030 (Open Web Text)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4882. Min Act: -0.1588

Data Index: 6621454 (Open Web Text)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4814. Min Act: -0.1667

Data Index: 2956559 (Open Web Text)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4479. Min Act: -0.1697

Data Index: 7899178 (Open Web Text)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4277. Min Act: -0.1535

Data Index: 4737797 (Open Web Text)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4301. Min Act: -0.1689

Data Index: 3472868 (Open Web Text)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4035. Min Act: -0.1677

Data Index: 5222333 (Open Web Text)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.4478. Min Act: -0.1228

Data Index: 3877515 (Open Web Text)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.7146. Min Range: -4.7146

Max Act: 4.3994. Min Act: -0.1695

Data Index: 808233 (Open Web Text)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #19