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

Dataset: Open Web Text

Neuron 1300 in Layer 4

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: 5.2720. Min Range: -5.2720

Max Act: 5.2720. Min Act: -0.1700

Data Index: 1774816 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 5.2720. Min Range: -5.2720

Max Act: 5.0937. Min Act: -0.1700

Data Index: 3986018 (Open Web Text)

Max Activating Token Index: 166

Text #2

Max Range: 5.2720. Min Range: -5.2720

Max Act: 5.1123. Min Act: -0.1700

Data Index: 2758220 (Open Web Text)

Max Activating Token Index: 891

Text #3

Max Range: 5.2720. Min Range: -5.2720

Max Act: 5.0381. Min Act: -0.1700

Data Index: 8785552 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 5.2720. Min Range: -5.2720

Max Act: 5.0208. Min Act: -0.1700

Data Index: 278392 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9710. Min Act: -0.1700

Data Index: 6224676 (Open Web Text)

Max Activating Token Index: 245

Text #6

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9611. Min Act: -0.1700

Data Index: 1002956 (Open Web Text)

Max Activating Token Index: 310

Text #7

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9851. Min Act: -0.1700

Data Index: 5684100 (Open Web Text)

Max Activating Token Index: 292

Text #8

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9700. Min Act: -0.1700

Data Index: 1322349 (Open Web Text)

Max Activating Token Index: 679

Text #9

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9088. Min Act: -0.1700

Data Index: 6143043 (Open Web Text)

Max Activating Token Index: 865

Text #10

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9487. Min Act: -0.1700

Data Index: 5294589 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9347. Min Act: -0.1700

Data Index: 5574236 (Open Web Text)

Max Activating Token Index: 141

Text #12

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9094. Min Act: -0.1700

Data Index: 1022167 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.8713. Min Act: -0.1700

Data Index: 2007090 (Open Web Text)

Max Activating Token Index: 492

Text #14

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9684. Min Act: -0.1700

Data Index: 5228148 (Open Web Text)

Max Activating Token Index: 570

Text #15

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.8782. Min Act: -0.1700

Data Index: 5842820 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.9133. Min Act: -0.1700

Data Index: 8488858 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.8619. Min Act: -0.1700

Data Index: 1184614 (Open Web Text)

Max Activating Token Index: 965

Text #18

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.7923. Min Act: -0.1700

Data Index: 4268646 (Open Web Text)

Max Activating Token Index: 304

Text #19

Max Range: 5.2720. Min Range: -5.2720

Max Act: 4.8691. Min Act: -0.1700

Data Index: 4866181 (Open Web Text)

Max Activating Token Index: 869