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

Dataset: Open Web Text

Neuron 2710 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: 6.6902. Min Range: -6.6902

Max Act: 6.6902. Min Act: -0.1700

Data Index: 3181440 (Open Web Text)

Max Activating Token Index: 700

Text #1

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.5495. Min Act: -0.1700

Data Index: 3077317 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.3744. Min Act: -0.1700

Data Index: 7746654 (Open Web Text)

Max Activating Token Index: 967

Text #3

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.3793. Min Act: -0.1700

Data Index: 2547487 (Open Web Text)

Max Activating Token Index: 915

Text #4

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.3502. Min Act: -0.1700

Data Index: 8195782 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.2950. Min Act: -0.1700

Data Index: 3360479 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.2453. Min Act: -0.1700

Data Index: 4546688 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.1624. Min Act: -0.1700

Data Index: 433179 (Open Web Text)

Max Activating Token Index: 983

Text #8

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.2278. Min Act: -0.1700

Data Index: 4300966 (Open Web Text)

Max Activating Token Index: 574

Text #9

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.1483. Min Act: -0.1700

Data Index: 2798435 (Open Web Text)

Max Activating Token Index: 737

Text #10

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.1640. Min Act: -0.1700

Data Index: 6414514 (Open Web Text)

Max Activating Token Index: 497

Text #11

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.0453. Min Act: -0.1700

Data Index: 2955769 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.0952. Min Act: -0.1700

Data Index: 4047822 (Open Web Text)

Max Activating Token Index: 650

Text #13

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.0513. Min Act: -0.1700

Data Index: 1735325 (Open Web Text)

Max Activating Token Index: 890

Text #14

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.0379. Min Act: -0.1700

Data Index: 3089569 (Open Web Text)

Max Activating Token Index: 43

Text #15

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.0328. Min Act: -0.1700

Data Index: 5604678 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.0285. Min Act: -0.1700

Data Index: 6906093 (Open Web Text)

Max Activating Token Index: 860

Text #17

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.0145. Min Act: -0.1700

Data Index: 713145 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 6.6902. Min Range: -6.6902

Max Act: 5.9741. Min Act: -0.1700

Data Index: 2549229 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 6.6902. Min Range: -6.6902

Max Act: 6.0228. Min Act: -0.1700

Data Index: 6565638 (Open Web Text)

Max Activating Token Index: 822