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

Dataset: Open Web Text

Neuron 2940 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: 4.1778. Min Range: -4.1778

Max Act: 4.1632. Min Act: -0.1700

Data Index: 751103 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.1778. Min Act: -0.1700

Data Index: 4799159 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.1248. Min Act: -0.1700

Data Index: 2574402 (Open Web Text)

Max Activating Token Index: 1016

Text #3

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.1038. Min Act: -0.1700

Data Index: 6672966 (Open Web Text)

Max Activating Token Index: 548

Text #4

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.1090. Min Act: -0.1700

Data Index: 5374796 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0502. Min Act: -0.1700

Data Index: 6611703 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0882. Min Act: -0.1700

Data Index: 1471821 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0915. Min Act: -0.1700

Data Index: 5424302 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0608. Min Act: -0.1700

Data Index: 6635212 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0663. Min Act: -0.1700

Data Index: 7843858 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0295. Min Act: -0.1700

Data Index: 6428817 (Open Web Text)

Max Activating Token Index: 911

Text #11

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.1065. Min Act: -0.1700

Data Index: 5830471 (Open Web Text)

Max Activating Token Index: 1009

Text #12

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0775. Min Act: -0.1700

Data Index: 4682573 (Open Web Text)

Max Activating Token Index: 1001

Text #13

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0670. Min Act: -0.1700

Data Index: 4455965 (Open Web Text)

Max Activating Token Index: 618

Text #14

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0785. Min Act: -0.1700

Data Index: 8240030 (Open Web Text)

Max Activating Token Index: 659

Text #15

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0387. Min Act: -0.1700

Data Index: 4892952 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0283. Min Act: -0.1700

Data Index: 5583902 (Open Web Text)

Max Activating Token Index: 984

Text #17

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0614. Min Act: -0.1700

Data Index: 3695202 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0301. Min Act: -0.1700

Data Index: 751104 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 4.1778. Min Range: -4.1778

Max Act: 4.0385. Min Act: -0.1700

Data Index: 6749270 (Open Web Text)

Max Activating Token Index: 256