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

Dataset: Open Web Text

Neuron 1812 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: 1.7400. Min Range: -1.7400

Max Act: 1.7400. Min Act: -0.1349

Data Index: 3731626 (Open Web Text)

Max Activating Token Index: 594

Text #1

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.7068. Min Act: -0.1699

Data Index: 891677 (Open Web Text)

Max Activating Token Index: 276

Text #2

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.7102. Min Act: -0.1685

Data Index: 6517057 (Open Web Text)

Max Activating Token Index: 690

Text #3

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6741. Min Act: -0.1699

Data Index: 4782778 (Open Web Text)

Max Activating Token Index: 973

Text #4

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6842. Min Act: -0.1482

Data Index: 6842453 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6949. Min Act: -0.1671

Data Index: 5381756 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6633. Min Act: -0.1656

Data Index: 7025408 (Open Web Text)

Max Activating Token Index: 711

Text #7

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6605. Min Act: -0.1700

Data Index: 2305966 (Open Web Text)

Max Activating Token Index: 955

Text #8

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6650. Min Act: -0.1626

Data Index: 3713347 (Open Web Text)

Max Activating Token Index: 1019

Text #9

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6668. Min Act: -0.1659

Data Index: 3011420 (Open Web Text)

Max Activating Token Index: 410

Text #10

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6556. Min Act: -0.1206

Data Index: 6143750 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6411. Min Act: -0.1700

Data Index: 7771012 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6419. Min Act: -0.1511

Data Index: 7343553 (Open Web Text)

Max Activating Token Index: 636

Text #13

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6556. Min Act: -0.1311

Data Index: 3857348 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6503. Min Act: -0.1563

Data Index: 740472 (Open Web Text)

Max Activating Token Index: 1000

Text #15

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6583. Min Act: -0.1356

Data Index: 3991587 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6535. Min Act: -0.1653

Data Index: 6918550 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6494. Min Act: -0.1700

Data Index: 1560266 (Open Web Text)

Max Activating Token Index: 855

Text #18

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6332. Min Act: -0.1581

Data Index: 503284 (Open Web Text)

Max Activating Token Index: 948

Text #19

Max Range: 1.7400. Min Range: -1.7400

Max Act: 1.6290. Min Act: -0.1517

Data Index: 6220012 (Open Web Text)

Max Activating Token Index: 687