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

Dataset: Open Web Text

Neuron 1863 in Layer 3

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: 4.1818. Min Range: -4.1818

Max Act: 4.1636. Min Act: -0.1700

Data Index: 7098400 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.1733. Min Act: -0.1700

Data Index: 7841354 (Open Web Text)

Max Activating Token Index: 695

Text #2

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.1818. Min Act: -0.1700

Data Index: 1482012 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.1025. Min Act: -0.1700

Data Index: 4874394 (Open Web Text)

Max Activating Token Index: 795

Text #4

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.1153. Min Act: -0.1700

Data Index: 6127209 (Open Web Text)

Max Activating Token Index: 204

Text #5

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.1164. Min Act: -0.1700

Data Index: 3750655 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0902. Min Act: -0.1700

Data Index: 6127207 (Open Web Text)

Max Activating Token Index: 955

Text #7

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0736. Min Act: -0.1700

Data Index: 1332922 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0846. Min Act: -0.1700

Data Index: 2221654 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0716. Min Act: -0.1700

Data Index: 6447383 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0678. Min Act: -0.1700

Data Index: 1187319 (Open Web Text)

Max Activating Token Index: 219

Text #11

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0996. Min Act: -0.1700

Data Index: 2631011 (Open Web Text)

Max Activating Token Index: 321

Text #12

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0300. Min Act: -0.1700

Data Index: 4263903 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0073. Min Act: -0.1700

Data Index: 4614809 (Open Web Text)

Max Activating Token Index: 405

Text #14

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0244. Min Act: -0.1700

Data Index: 7574403 (Open Web Text)

Max Activating Token Index: 948

Text #15

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0427. Min Act: -0.1700

Data Index: 6236190 (Open Web Text)

Max Activating Token Index: 272

Text #16

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0893. Min Act: -0.1700

Data Index: 2509759 (Open Web Text)

Max Activating Token Index: 868

Text #17

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0727. Min Act: -0.1700

Data Index: 553668 (Open Web Text)

Max Activating Token Index: 802

Text #18

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0011. Min Act: -0.1700

Data Index: 1242769 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 4.1818. Min Range: -4.1818

Max Act: 4.0299. Min Act: -0.1700

Data Index: 1297054 (Open Web Text)

Max Activating Token Index: 419