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

Dataset: Open Web Text

Neuron 2485 in Layer 6

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: 3.3262. Min Range: -3.3262

Max Act: 3.3262. Min Act: -0.1700

Data Index: 4259446 (Open Web Text)

Max Activating Token Index: 903

Text #1

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.2416. Min Act: -0.1700

Data Index: 6852829 (Open Web Text)

Max Activating Token Index: 899

Text #2

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.2208. Min Act: -0.1700

Data Index: 932303 (Open Web Text)

Max Activating Token Index: 942

Text #3

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1730. Min Act: -0.1700

Data Index: 5370459 (Open Web Text)

Max Activating Token Index: 940

Text #4

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1674. Min Act: -0.1700

Data Index: 3743479 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1601. Min Act: -0.1700

Data Index: 1909411 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1300. Min Act: -0.1700

Data Index: 1541747 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1008. Min Act: -0.1700

Data Index: 2302614 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.1136. Min Act: -0.1700

Data Index: 4309522 (Open Web Text)

Max Activating Token Index: 972

Text #9

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0848. Min Act: -0.1700

Data Index: 3174353 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0923. Min Act: -0.1700

Data Index: 4060523 (Open Web Text)

Max Activating Token Index: 934

Text #11

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0632. Min Act: -0.1700

Data Index: 8497181 (Open Web Text)

Max Activating Token Index: 1018

Text #12

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0754. Min Act: -0.1700

Data Index: 4612527 (Open Web Text)

Max Activating Token Index: 899

Text #13

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0478. Min Act: -0.1700

Data Index: 8676928 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0330. Min Act: -0.1700

Data Index: 6429923 (Open Web Text)

Max Activating Token Index: 808

Text #15

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0229. Min Act: -0.1700

Data Index: 2571442 (Open Web Text)

Max Activating Token Index: 533

Text #16

Max Range: 3.3262. Min Range: -3.3262

Max Act: 3.0200. Min Act: -0.1700

Data Index: 3148097 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 3.3262. Min Range: -3.3262

Max Act: 2.9995. Min Act: -0.1700

Data Index: 4395778 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 3.3262. Min Range: -3.3262

Max Act: 2.9654. Min Act: -0.1700

Data Index: 2744014 (Open Web Text)

Max Activating Token Index: 430

Text #19

Max Range: 3.3262. Min Range: -3.3262

Max Act: 2.9139. Min Act: -0.1700

Data Index: 4715023 (Open Web Text)

Max Activating Token Index: 1014