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

Dataset: Open Web Text

Neuron 1134 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: 1.5677. Min Range: -1.5677

Max Act: 1.5677. Min Act: -0.1684

Data Index: 5899476 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5374. Min Act: -0.1679

Data Index: 1789572 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5175. Min Act: -0.1672

Data Index: 221145 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5172. Min Act: -0.1700

Data Index: 7700178 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5065. Min Act: -0.1700

Data Index: 838058 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5095. Min Act: -0.1625

Data Index: 7208570 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5047. Min Act: -0.1695

Data Index: 6930881 (Open Web Text)

Max Activating Token Index: 49

Text #7

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5031. Min Act: -0.1675

Data Index: 5312794 (Open Web Text)

Max Activating Token Index: 470

Text #8

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5231. Min Act: -0.1700

Data Index: 7701619 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5042. Min Act: -0.1692

Data Index: 4656773 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4945. Min Act: -0.1631

Data Index: 5938029 (Open Web Text)

Max Activating Token Index: 626

Text #11

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.5024. Min Act: -0.1681

Data Index: 4580624 (Open Web Text)

Max Activating Token Index: 908

Text #12

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4775. Min Act: -0.1700

Data Index: 3580817 (Open Web Text)

Max Activating Token Index: 649

Text #13

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4954. Min Act: -0.1693

Data Index: 6693796 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4962. Min Act: -0.1686

Data Index: 6102665 (Open Web Text)

Max Activating Token Index: 931

Text #15

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4859. Min Act: -0.1700

Data Index: 6937889 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4891. Min Act: -0.1615

Data Index: 1124848 (Open Web Text)

Max Activating Token Index: 257

Text #17

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4840. Min Act: -0.1698

Data Index: 2218240 (Open Web Text)

Max Activating Token Index: 489

Text #18

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4759. Min Act: -0.1700

Data Index: 6798688 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 1.5677. Min Range: -1.5677

Max Act: 1.4766. Min Act: -0.1635

Data Index: 5691883 (Open Web Text)

Max Activating Token Index: 308