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

Dataset: Open Web Text

Neuron 2551 in Layer 2

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: 3.3902. Min Range: -3.3902

Max Act: 3.3902. Min Act: -0.1700

Data Index: 82756 (Open Web Text)

Max Activating Token Index: 693

Text #1

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.3875. Min Act: -0.1700

Data Index: 8602462 (Open Web Text)

Max Activating Token Index: 949

Text #2

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.3733. Min Act: -0.1700

Data Index: 5476770 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.3316. Min Act: -0.1700

Data Index: 950799 (Open Web Text)

Max Activating Token Index: 282

Text #4

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.3094. Min Act: -0.1700

Data Index: 1867462 (Open Web Text)

Max Activating Token Index: 919

Text #5

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.3122. Min Act: -0.1700

Data Index: 6722313 (Open Web Text)

Max Activating Token Index: 452

Text #6

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2909. Min Act: -0.1700

Data Index: 977150 (Open Web Text)

Max Activating Token Index: 403

Text #7

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2937. Min Act: -0.1700

Data Index: 3903028 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2877. Min Act: -0.1700

Data Index: 3653747 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2763. Min Act: -0.1700

Data Index: 1468664 (Open Web Text)

Max Activating Token Index: 175

Text #10

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2921. Min Act: -0.1700

Data Index: 7277830 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2746. Min Act: -0.1700

Data Index: 332581 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2632. Min Act: -0.1700

Data Index: 4163451 (Open Web Text)

Max Activating Token Index: 486

Text #13

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2657. Min Act: -0.1700

Data Index: 2711291 (Open Web Text)

Max Activating Token Index: 987

Text #14

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2846. Min Act: -0.1700

Data Index: 5914422 (Open Web Text)

Max Activating Token Index: 188

Text #15

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2761. Min Act: -0.1700

Data Index: 1339847 (Open Web Text)

Max Activating Token Index: 788

Text #16

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2690. Min Act: -0.1700

Data Index: 7256715 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2520. Min Act: -0.1700

Data Index: 6855505 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2657. Min Act: -0.1700

Data Index: 1667564 (Open Web Text)

Max Activating Token Index: 137

Text #19

Max Range: 3.3902. Min Range: -3.3902

Max Act: 3.2474. Min Act: -0.1700

Data Index: 2548636 (Open Web Text)

Max Activating Token Index: 14