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

Dataset: Open Web Text

Neuron 2764 in Layer 0

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: 4.7989. Min Range: -4.7989

Max Act: 4.7989. Min Act: -0.1700

Data Index: 3405362 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.7616. Min Act: -0.1700

Data Index: 3005358 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.7267. Min Act: -0.1700

Data Index: 6037542 (Open Web Text)

Max Activating Token Index: 800

Text #3

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.7307. Min Act: -0.1700

Data Index: 2173776 (Open Web Text)

Max Activating Token Index: 770

Text #4

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.7169. Min Act: -0.1700

Data Index: 2043619 (Open Web Text)

Max Activating Token Index: 48

Text #5

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.7207. Min Act: -0.1700

Data Index: 4497986 (Open Web Text)

Max Activating Token Index: 26

Text #6

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6858. Min Act: -0.1700

Data Index: 215977 (Open Web Text)

Max Activating Token Index: 987

Text #7

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6846. Min Act: -0.1700

Data Index: 466193 (Open Web Text)

Max Activating Token Index: 736

Text #8

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6801. Min Act: -0.1700

Data Index: 1234256 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6980. Min Act: -0.1700

Data Index: 2173777 (Open Web Text)

Max Activating Token Index: 706

Text #10

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6506. Min Act: -0.1700

Data Index: 2869073 (Open Web Text)

Max Activating Token Index: 42

Text #11

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6734. Min Act: -0.1700

Data Index: 3951059 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6464. Min Act: -0.1700

Data Index: 3472914 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6613. Min Act: -0.1700

Data Index: 697367 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6563. Min Act: -0.1700

Data Index: 3409496 (Open Web Text)

Max Activating Token Index: 1000

Text #15

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6649. Min Act: -0.1700

Data Index: 6551018 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6548. Min Act: -0.1700

Data Index: 6914337 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6435. Min Act: -0.1700

Data Index: 1148988 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6753. Min Act: -0.1700

Data Index: 2485369 (Open Web Text)

Max Activating Token Index: 931

Text #19

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6633. Min Act: -0.1700

Data Index: 626106 (Open Web Text)

Max Activating Token Index: 18