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

Dataset: Open Web Text

Neuron 2880 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: 3.0902. Min Range: -3.0902

Max Act: 3.0833. Min Act: -0.1700

Data Index: 846678 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 3.0902. Min Range: -3.0902

Max Act: 3.0902. Min Act: -0.1700

Data Index: 1063907 (Open Web Text)

Max Activating Token Index: 937

Text #2

Max Range: 3.0902. Min Range: -3.0902

Max Act: 3.0618. Min Act: -0.1700

Data Index: 4529347 (Open Web Text)

Max Activating Token Index: 611

Text #3

Max Range: 3.0902. Min Range: -3.0902

Max Act: 3.0699. Min Act: -0.1700

Data Index: 3404998 (Open Web Text)

Max Activating Token Index: 870

Text #4

Max Range: 3.0902. Min Range: -3.0902

Max Act: 3.0551. Min Act: -0.1700

Data Index: 6754812 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 3.0902. Min Range: -3.0902

Max Act: 3.0473. Min Act: -0.1700

Data Index: 8047625 (Open Web Text)

Max Activating Token Index: 295

Text #6

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9669. Min Act: -0.1700

Data Index: 5272788 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 3.0902. Min Range: -3.0902

Max Act: 3.0009. Min Act: -0.1700

Data Index: 4173345 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9946. Min Act: -0.1700

Data Index: 7728649 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9749. Min Act: -0.1700

Data Index: 4881777 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9822. Min Act: -0.1700

Data Index: 8336219 (Open Web Text)

Max Activating Token Index: 168

Text #11

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9907. Min Act: -0.1700

Data Index: 188198 (Open Web Text)

Max Activating Token Index: 1017

Text #12

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9785. Min Act: -0.1700

Data Index: 796260 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9784. Min Act: -0.1700

Data Index: 4375310 (Open Web Text)

Max Activating Token Index: 904

Text #14

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9395. Min Act: -0.1700

Data Index: 2606502 (Open Web Text)

Max Activating Token Index: 633

Text #15

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9404. Min Act: -0.1700

Data Index: 2744207 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9718. Min Act: -0.1700

Data Index: 8710199 (Open Web Text)

Max Activating Token Index: 218

Text #17

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9751. Min Act: -0.1700

Data Index: 3723104 (Open Web Text)

Max Activating Token Index: 885

Text #18

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9348. Min Act: -0.1700

Data Index: 8073205 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 3.0902. Min Range: -3.0902

Max Act: 2.9499. Min Act: -0.1700

Data Index: 2471665 (Open Web Text)

Max Activating Token Index: 597