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

Dataset: Open Web Text

Neuron 2767 in Layer 5

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: 3.8759. Min Range: -3.8759

Max Act: 3.8759. Min Act: -0.1700

Data Index: 4036427 (Open Web Text)

Max Activating Token Index: 974

Text #1

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8150. Min Act: -0.1700

Data Index: 232902 (Open Web Text)

Max Activating Token Index: 701

Text #2

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.8169. Min Act: -0.1700

Data Index: 7033849 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7866. Min Act: -0.1700

Data Index: 7033850 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7630. Min Act: -0.1700

Data Index: 2000133 (Open Web Text)

Max Activating Token Index: 828

Text #5

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7176. Min Act: -0.1700

Data Index: 345705 (Open Web Text)

Max Activating Token Index: 863

Text #6

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6964. Min Act: -0.1700

Data Index: 5148157 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6779. Min Act: -0.1700

Data Index: 6789932 (Open Web Text)

Max Activating Token Index: 623

Text #8

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.7014. Min Act: -0.1700

Data Index: 3437727 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6767. Min Act: -0.1700

Data Index: 8315863 (Open Web Text)

Max Activating Token Index: 855

Text #10

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6553. Min Act: -0.1700

Data Index: 3580822 (Open Web Text)

Max Activating Token Index: 632

Text #11

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6985. Min Act: -0.1700

Data Index: 7078310 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6748. Min Act: -0.1700

Data Index: 4508535 (Open Web Text)

Max Activating Token Index: 328

Text #13

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6718. Min Act: -0.1700

Data Index: 8305651 (Open Web Text)

Max Activating Token Index: 967

Text #14

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6917. Min Act: -0.1700

Data Index: 3778977 (Open Web Text)

Max Activating Token Index: 1002

Text #15

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6501. Min Act: -0.1700

Data Index: 1158167 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6506. Min Act: -0.1700

Data Index: 3938155 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6328. Min Act: -0.1700

Data Index: 1985776 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6291. Min Act: -0.1700

Data Index: 4226195 (Open Web Text)

Max Activating Token Index: 852

Text #19

Max Range: 3.8759. Min Range: -3.8759

Max Act: 3.6440. Min Act: -0.1700

Data Index: 2466184 (Open Web Text)

Max Activating Token Index: 525