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

Dataset: Open Web Text

Neuron 438 in Layer 0

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: 2.2736. Min Range: -2.2736

Max Act: 2.2736. Min Act: -0.1700

Data Index: 1344756 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.2118. Min Act: -0.1676

Data Index: 4759702 (Open Web Text)

Max Activating Token Index: 384

Text #2

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.2156. Min Act: -0.1696

Data Index: 1306767 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1955. Min Act: -0.1693

Data Index: 3104712 (Open Web Text)

Max Activating Token Index: 568

Text #4

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1952. Min Act: -0.1699

Data Index: 8406917 (Open Web Text)

Max Activating Token Index: 565

Text #5

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1788. Min Act: -0.1700

Data Index: 5689453 (Open Web Text)

Max Activating Token Index: 551

Text #6

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1859. Min Act: -0.1700

Data Index: 2429778 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1820. Min Act: -0.1694

Data Index: 7865800 (Open Web Text)

Max Activating Token Index: 632

Text #8

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1871. Min Act: -0.1685

Data Index: 7249434 (Open Web Text)

Max Activating Token Index: 638

Text #9

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1709. Min Act: -0.1695

Data Index: 2259575 (Open Web Text)

Max Activating Token Index: 435

Text #10

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1602. Min Act: -0.1700

Data Index: 8733274 (Open Web Text)

Max Activating Token Index: 707

Text #11

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1695. Min Act: -0.1700

Data Index: 701401 (Open Web Text)

Max Activating Token Index: 374

Text #12

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1725. Min Act: -0.1699

Data Index: 385694 (Open Web Text)

Max Activating Token Index: 370

Text #13

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1680. Min Act: -0.1700

Data Index: 6853605 (Open Web Text)

Max Activating Token Index: 939

Text #14

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1671. Min Act: -0.1700

Data Index: 3417564 (Open Web Text)

Max Activating Token Index: 346

Text #15

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1612. Min Act: -0.1700

Data Index: 5958115 (Open Web Text)

Max Activating Token Index: 1019

Text #16

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1756. Min Act: -0.1696

Data Index: 2460733 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1637. Min Act: -0.1691

Data Index: 1306766 (Open Web Text)

Max Activating Token Index: 584

Text #18

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1683. Min Act: -0.1700

Data Index: 4643702 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 2.2736. Min Range: -2.2736

Max Act: 2.1589. Min Act: -0.1700

Data Index: 504624 (Open Web Text)

Max Activating Token Index: 946