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

Dataset: Open Web Text

Neuron 1974 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: 1.7443. Min Range: -1.7443

Max Act: 1.7443. Min Act: -0.1697

Data Index: 8524809 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7368. Min Act: -0.1678

Data Index: 150386 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7244. Min Act: -0.1700

Data Index: 7072126 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7254. Min Act: -0.1700

Data Index: 2211310 (Open Web Text)

Max Activating Token Index: 460

Text #4

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7155. Min Act: -0.1687

Data Index: 2982227 (Open Web Text)

Max Activating Token Index: 757

Text #5

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7185. Min Act: -0.1682

Data Index: 1652888 (Open Web Text)

Max Activating Token Index: 692

Text #6

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7133. Min Act: -0.1700

Data Index: 2918083 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7098. Min Act: -0.1700

Data Index: 5649966 (Open Web Text)

Max Activating Token Index: 437

Text #8

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7075. Min Act: -0.1696

Data Index: 7612606 (Open Web Text)

Max Activating Token Index: 615

Text #9

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6951. Min Act: -0.1668

Data Index: 1243240 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6928. Min Act: -0.1700

Data Index: 352656 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.7038. Min Act: -0.1677

Data Index: 2068127 (Open Web Text)

Max Activating Token Index: 844

Text #12

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6923. Min Act: -0.1696

Data Index: 1368173 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6840. Min Act: -0.1700

Data Index: 7572695 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6923. Min Act: -0.1692

Data Index: 7095373 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6763. Min Act: -0.1699

Data Index: 565562 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6788. Min Act: -0.1700

Data Index: 1779981 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6773. Min Act: -0.1700

Data Index: 4813756 (Open Web Text)

Max Activating Token Index: 194

Text #18

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6945. Min Act: -0.1656

Data Index: 1946192 (Open Web Text)

Max Activating Token Index: 896

Text #19

Max Range: 1.7443. Min Range: -1.7443

Max Act: 1.6785. Min Act: -0.1700

Data Index: 1070666 (Open Web Text)

Max Activating Token Index: 11