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

Dataset: Open Web Text

Neuron 2916 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: 1.2200. Min Range: -1.2200

Max Act: 1.2200. Min Act: -0.1561

Data Index: 4548775 (Open Web Text)

Max Activating Token Index: 705

Text #1

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.2074. Min Act: -0.1272

Data Index: 6428658 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.2076. Min Act: -0.1461

Data Index: 3973108 (Open Web Text)

Max Activating Token Index: 371

Text #3

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.2048. Min Act: -0.1677

Data Index: 982836 (Open Web Text)

Max Activating Token Index: 751

Text #4

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.2013. Min Act: -0.1659

Data Index: 5936558 (Open Web Text)

Max Activating Token Index: 664

Text #5

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1849. Min Act: -0.1470

Data Index: 2598841 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1974. Min Act: -0.1476

Data Index: 2256666 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1865. Min Act: -0.1675

Data Index: 1566286 (Open Web Text)

Max Activating Token Index: 929

Text #8

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1834. Min Act: -0.1566

Data Index: 2420902 (Open Web Text)

Max Activating Token Index: 1008

Text #9

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1825. Min Act: -0.1578

Data Index: 7412998 (Open Web Text)

Max Activating Token Index: 803

Text #10

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1694. Min Act: -0.1516

Data Index: 1594272 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1727. Min Act: -0.1440

Data Index: 4807778 (Open Web Text)

Max Activating Token Index: 756

Text #12

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1708. Min Act: -0.1640

Data Index: 3151447 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1671. Min Act: -0.1515

Data Index: 405557 (Open Web Text)

Max Activating Token Index: 865

Text #14

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1704. Min Act: -0.1680

Data Index: 2608167 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1686. Min Act: -0.1631

Data Index: 1554299 (Open Web Text)

Max Activating Token Index: 884

Text #16

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1630. Min Act: -0.1179

Data Index: 609765 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1607. Min Act: -0.1647

Data Index: 1742124 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1626. Min Act: -0.1476

Data Index: 48790 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1585. Min Act: -0.1661

Data Index: 3886749 (Open Web Text)

Max Activating Token Index: 607