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

Dataset: Open Web Text

Neuron 2979 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: 6.6793. Min Range: -6.6793

Max Act: 6.6793. Min Act: -0.1700

Data Index: 1687289 (Open Web Text)

Max Activating Token Index: 897

Text #1

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.6621. Min Act: -0.1700

Data Index: 4089986 (Open Web Text)

Max Activating Token Index: 787

Text #2

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.5891. Min Act: -0.1700

Data Index: 2787190 (Open Web Text)

Max Activating Token Index: 858

Text #3

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.6423. Min Act: -0.1700

Data Index: 8700697 (Open Web Text)

Max Activating Token Index: 259

Text #4

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.5778. Min Act: -0.1700

Data Index: 986913 (Open Web Text)

Max Activating Token Index: 668

Text #5

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.5526. Min Act: -0.1700

Data Index: 2510262 (Open Web Text)

Max Activating Token Index: 738

Text #6

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.5711. Min Act: -0.1700

Data Index: 4099210 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.5696. Min Act: -0.1700

Data Index: 6510243 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.5155. Min Act: -0.1700

Data Index: 3344967 (Open Web Text)

Max Activating Token Index: 367

Text #9

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4868. Min Act: -0.1700

Data Index: 201824 (Open Web Text)

Max Activating Token Index: 448

Text #10

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4634. Min Act: -0.1700

Data Index: 4904367 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4827. Min Act: -0.1700

Data Index: 2296677 (Open Web Text)

Max Activating Token Index: 947

Text #12

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4922. Min Act: -0.1700

Data Index: 6536643 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4687. Min Act: -0.1700

Data Index: 7399477 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4915. Min Act: -0.1700

Data Index: 8406433 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.5183. Min Act: -0.1700

Data Index: 84513 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4641. Min Act: -0.1700

Data Index: 1714468 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.3939. Min Act: -0.1700

Data Index: 4423501 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4015. Min Act: -0.1700

Data Index: 1837471 (Open Web Text)

Max Activating Token Index: 678

Text #19

Max Range: 6.6793. Min Range: -6.6793

Max Act: 6.4411. Min Act: -0.1700

Data Index: 1389879 (Open Web Text)

Max Activating Token Index: 972