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

Dataset: Open Web Text

Neuron 1342 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: 1.5583. Min Range: -1.5583

Max Act: 1.5583. Min Act: -0.1690

Data Index: 8312320 (Open Web Text)

Max Activating Token Index: 202

Text #1

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5321. Min Act: -0.1689

Data Index: 12484 (Open Web Text)

Max Activating Token Index: 759

Text #2

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5199. Min Act: -0.1686

Data Index: 3477822 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5301. Min Act: -0.1662

Data Index: 1969796 (Open Web Text)

Max Activating Token Index: 364

Text #4

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5251. Min Act: -0.1660

Data Index: 1850172 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5134. Min Act: -0.1008

Data Index: 6317208 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5155. Min Act: -0.1577

Data Index: 7500065 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5072. Min Act: -0.1576

Data Index: 6151677 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4988. Min Act: -0.1580

Data Index: 1367172 (Open Web Text)

Max Activating Token Index: 761

Text #9

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4976. Min Act: -0.1646

Data Index: 3521214 (Open Web Text)

Max Activating Token Index: 29

Text #10

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4834. Min Act: -0.1693

Data Index: 336894 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4967. Min Act: -0.1690

Data Index: 2063479 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4876. Min Act: -0.1557

Data Index: 6128243 (Open Web Text)

Max Activating Token Index: 42

Text #13

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4952. Min Act: -0.1477

Data Index: 138005 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4846. Min Act: -0.1676

Data Index: 5454693 (Open Web Text)

Max Activating Token Index: 314

Text #15

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4840. Min Act: -0.1583

Data Index: 742 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4823. Min Act: -0.1691

Data Index: 8594201 (Open Web Text)

Max Activating Token Index: 35

Text #17

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4892. Min Act: -0.1695

Data Index: 4210031 (Open Web Text)

Max Activating Token Index: 652

Text #18

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4901. Min Act: -0.1700

Data Index: 1138542 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.4761. Min Act: -0.1350

Data Index: 3835598 (Open Web Text)

Max Activating Token Index: 671