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

Dataset: Open Web Text

Neuron 2342 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: 1.2268. Min Range: -1.2268

Max Act: 1.2266. Min Act: -0.1416

Data Index: 4243377 (Open Web Text)

Max Activating Token Index: 1018

Text #1

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.2268. Min Act: -0.1588

Data Index: 6312859 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.2247. Min Act: -0.1643

Data Index: 5018476 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.2218. Min Act: -0.1432

Data Index: 1456137 (Open Web Text)

Max Activating Token Index: 982

Text #4

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.2230. Min Act: -0.1608

Data Index: 2892713 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.2128. Min Act: -0.1402

Data Index: 8596887 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.2011. Min Act: -0.1424

Data Index: 6268702 (Open Web Text)

Max Activating Token Index: 761

Text #7

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1870. Min Act: -0.1666

Data Index: 8599288 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1889. Min Act: -0.1600

Data Index: 7300855 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1891. Min Act: -0.1567

Data Index: 1375451 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1821. Min Act: -0.1582

Data Index: 5015297 (Open Web Text)

Max Activating Token Index: 986

Text #11

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1875. Min Act: -0.1593

Data Index: 410564 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1916. Min Act: -0.1568

Data Index: 3047876 (Open Web Text)

Max Activating Token Index: 1010

Text #13

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1711. Min Act: -0.1484

Data Index: 3098443 (Open Web Text)

Max Activating Token Index: 127

Text #14

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1734. Min Act: -0.1596

Data Index: 3179528 (Open Web Text)

Max Activating Token Index: 165

Text #15

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1794. Min Act: -0.1700

Data Index: 4930385 (Open Web Text)

Max Activating Token Index: 945

Text #16

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1775. Min Act: -0.1588

Data Index: 2414753 (Open Web Text)

Max Activating Token Index: 1015

Text #17

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1790. Min Act: -0.1468

Data Index: 3427743 (Open Web Text)

Max Activating Token Index: 656

Text #18

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1808. Min Act: -0.1379

Data Index: 4692273 (Open Web Text)

Max Activating Token Index: 1002

Text #19

Max Range: 1.2268. Min Range: -1.2268

Max Act: 1.1703. Min Act: -0.1484

Data Index: 1932115 (Open Web Text)

Max Activating Token Index: 156