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

Dataset: Open Web Text

Neuron 1962 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: 4.6546. Min Range: -4.6546

Max Act: 4.6546. Min Act: -0.1700

Data Index: 2759056 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.4229. Min Act: -0.1700

Data Index: 1900073 (Open Web Text)

Max Activating Token Index: 328

Text #2

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.3531. Min Act: -0.1700

Data Index: 5678223 (Open Web Text)

Max Activating Token Index: 167

Text #3

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.3495. Min Act: -0.1700

Data Index: 8018247 (Open Web Text)

Max Activating Token Index: 907

Text #4

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2583. Min Act: -0.1700

Data Index: 2743512 (Open Web Text)

Max Activating Token Index: 916

Text #5

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2558. Min Act: -0.1700

Data Index: 1537788 (Open Web Text)

Max Activating Token Index: 753

Text #6

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2355. Min Act: -0.1700

Data Index: 3628169 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2754. Min Act: -0.1700

Data Index: 3110901 (Open Web Text)

Max Activating Token Index: 778

Text #8

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2642. Min Act: -0.1700

Data Index: 1370834 (Open Web Text)

Max Activating Token Index: 206

Text #9

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2126. Min Act: -0.1700

Data Index: 5614473 (Open Web Text)

Max Activating Token Index: 643

Text #10

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.1815. Min Act: -0.1700

Data Index: 3535371 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2043. Min Act: -0.1700

Data Index: 8549800 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2644. Min Act: -0.1700

Data Index: 468588 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.1650. Min Act: -0.1700

Data Index: 7370748 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2205. Min Act: -0.1700

Data Index: 2189645 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2714. Min Act: -0.1700

Data Index: 7118283 (Open Web Text)

Max Activating Token Index: 891

Text #16

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.1971. Min Act: -0.1700

Data Index: 1294367 (Open Web Text)

Max Activating Token Index: 743

Text #17

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2132. Min Act: -0.1700

Data Index: 6700384 (Open Web Text)

Max Activating Token Index: 416

Text #18

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2013. Min Act: -0.1700

Data Index: 1570170 (Open Web Text)

Max Activating Token Index: 791

Text #19

Max Range: 4.6546. Min Range: -4.6546

Max Act: 4.2445. Min Act: -0.1700

Data Index: 520130 (Open Web Text)

Max Activating Token Index: 828