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

Dataset: Open Web Text

Neuron 1638 in Layer 1

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: 0.1917. Min Range: -0.1917

Max Act: 0.1882. Min Act: -0.1692

Data Index: 5370436 (Open Web Text)

Max Activating Token Index: 277

Text #1

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1917. Min Act: -0.1697

Data Index: 1548652 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1741. Min Act: -0.1696

Data Index: 7760426 (Open Web Text)

Max Activating Token Index: 826

Text #3

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1736. Min Act: -0.1683

Data Index: 8408640 (Open Web Text)

Max Activating Token Index: 614

Text #4

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1660. Min Act: -0.1673

Data Index: 6323627 (Open Web Text)

Max Activating Token Index: 763

Text #5

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1657. Min Act: -0.1673

Data Index: 7097410 (Open Web Text)

Max Activating Token Index: 1018

Text #6

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1571. Min Act: -0.1699

Data Index: 2962013 (Open Web Text)

Max Activating Token Index: 582

Text #7

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1554. Min Act: -0.1673

Data Index: 8079008 (Open Web Text)

Max Activating Token Index: 96

Text #8

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1510. Min Act: -0.1686

Data Index: 1826071 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1562. Min Act: -0.1673

Data Index: 1357160 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1521. Min Act: -0.1673

Data Index: 586584 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1492. Min Act: -0.1700

Data Index: 5594456 (Open Web Text)

Max Activating Token Index: 254

Text #12

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1527. Min Act: -0.1673

Data Index: 7448792 (Open Web Text)

Max Activating Token Index: 180

Text #13

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1509. Min Act: -0.1673

Data Index: 3875387 (Open Web Text)

Max Activating Token Index: 415

Text #14

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1436. Min Act: -0.1673

Data Index: 8189054 (Open Web Text)

Max Activating Token Index: 233

Text #15

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1479. Min Act: -0.1673

Data Index: 3958007 (Open Web Text)

Max Activating Token Index: 894

Text #16

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1475. Min Act: -0.1673

Data Index: 2892592 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1402. Min Act: -0.1673

Data Index: 435902 (Open Web Text)

Max Activating Token Index: 999

Text #18

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1409. Min Act: -0.1685

Data Index: 8489765 (Open Web Text)

Max Activating Token Index: 688

Text #19

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1399. Min Act: -0.1673

Data Index: 4494800 (Open Web Text)

Max Activating Token Index: 954