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

Dataset: Open Web Text

Neuron 1886 in Layer 4

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: 1.2961. Min Range: -1.2961

Max Act: 1.2961. Min Act: -0.1700

Data Index: 8827098 (Open Web Text)

Max Activating Token Index: 734

Text #1

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.2444. Min Act: -0.1700

Data Index: 2509830 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.2315. Min Act: -0.1700

Data Index: 3001631 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.2069. Min Act: -0.1700

Data Index: 3971663 (Open Web Text)

Max Activating Token Index: 709

Text #4

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1934. Min Act: -0.1700

Data Index: 1979219 (Open Web Text)

Max Activating Token Index: 719

Text #5

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.2175. Min Act: -0.1700

Data Index: 3722865 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.2053. Min Act: -0.1700

Data Index: 1225453 (Open Web Text)

Max Activating Token Index: 694

Text #7

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.2042. Min Act: -0.1700

Data Index: 5763797 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1978. Min Act: -0.1700

Data Index: 6354155 (Open Web Text)

Max Activating Token Index: 687

Text #9

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1924. Min Act: -0.1700

Data Index: 3020333 (Open Web Text)

Max Activating Token Index: 694

Text #10

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1857. Min Act: -0.1700

Data Index: 6438838 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1882. Min Act: -0.1700

Data Index: 376008 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1922. Min Act: -0.1700

Data Index: 6966633 (Open Web Text)

Max Activating Token Index: 691

Text #13

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1944. Min Act: -0.1700

Data Index: 1848272 (Open Web Text)

Max Activating Token Index: 744

Text #14

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1862. Min Act: -0.1700

Data Index: 8066576 (Open Web Text)

Max Activating Token Index: 656

Text #15

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1898. Min Act: -0.1700

Data Index: 8578896 (Open Web Text)

Max Activating Token Index: 667

Text #16

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1759. Min Act: -0.1700

Data Index: 720494 (Open Web Text)

Max Activating Token Index: 699

Text #17

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1759. Min Act: -0.1700

Data Index: 2660460 (Open Web Text)

Max Activating Token Index: 658

Text #18

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1801. Min Act: -0.1700

Data Index: 1407374 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 1.2961. Min Range: -1.2961

Max Act: 1.1710. Min Act: -0.1700

Data Index: 3695245 (Open Web Text)

Max Activating Token Index: 779