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

Dataset: Open Web Text

Neuron 2888 in Layer 3

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: 4.8556. Min Range: -4.8556

Max Act: 4.8556. Min Act: -0.1700

Data Index: 4811612 (Open Web Text)

Max Activating Token Index: 892

Text #1

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.8065. Min Act: -0.1700

Data Index: 3372025 (Open Web Text)

Max Activating Token Index: 975

Text #2

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.7840. Min Act: -0.1700

Data Index: 8623911 (Open Web Text)

Max Activating Token Index: 750

Text #3

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.7723. Min Act: -0.1700

Data Index: 657608 (Open Web Text)

Max Activating Token Index: 1000

Text #4

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.7759. Min Act: -0.1700

Data Index: 4850789 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.7637. Min Act: -0.1700

Data Index: 7576882 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.7833. Min Act: -0.1700

Data Index: 908640 (Open Web Text)

Max Activating Token Index: 962

Text #7

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.7105. Min Act: -0.1700

Data Index: 5640589 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.7142. Min Act: -0.1700

Data Index: 4643406 (Open Web Text)

Max Activating Token Index: 759

Text #9

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.7302. Min Act: -0.1700

Data Index: 1799912 (Open Web Text)

Max Activating Token Index: 713

Text #10

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6824. Min Act: -0.1700

Data Index: 7621341 (Open Web Text)

Max Activating Token Index: 694

Text #11

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6953. Min Act: -0.1700

Data Index: 8090420 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6701. Min Act: -0.1700

Data Index: 6178469 (Open Web Text)

Max Activating Token Index: 933

Text #13

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6524. Min Act: -0.1700

Data Index: 1743592 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6438. Min Act: -0.1700

Data Index: 7667428 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6431. Min Act: -0.1700

Data Index: 8069566 (Open Web Text)

Max Activating Token Index: 581

Text #16

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6029. Min Act: -0.1700

Data Index: 5177519 (Open Web Text)

Max Activating Token Index: 960

Text #17

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6353. Min Act: -0.1700

Data Index: 2384278 (Open Web Text)

Max Activating Token Index: 950

Text #18

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6126. Min Act: -0.1700

Data Index: 6676408 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 4.8556. Min Range: -4.8556

Max Act: 4.6208. Min Act: -0.1700

Data Index: 7138485 (Open Web Text)

Max Activating Token Index: 785