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

Dataset: Open Web Text

Neuron 3071 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: 3.9111. Min Range: -3.9111

Max Act: 3.8878. Min Act: -0.1700

Data Index: 5614059 (Open Web Text)

Max Activating Token Index: 335

Text #1

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.9111. Min Act: -0.1700

Data Index: 2943000 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.8491. Min Act: -0.1700

Data Index: 3527003 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.8555. Min Act: -0.1700

Data Index: 4232239 (Open Web Text)

Max Activating Token Index: 274

Text #4

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.8706. Min Act: -0.1700

Data Index: 4541049 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.8329. Min Act: -0.1700

Data Index: 4084961 (Open Web Text)

Max Activating Token Index: 228

Text #6

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.8215. Min Act: -0.1700

Data Index: 8530868 (Open Web Text)

Max Activating Token Index: 993

Text #7

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.8676. Min Act: -0.1700

Data Index: 4450991 (Open Web Text)

Max Activating Token Index: 943

Text #8

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7860. Min Act: -0.1700

Data Index: 6273568 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7805. Min Act: -0.1700

Data Index: 3027108 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7513. Min Act: -0.1700

Data Index: 8811107 (Open Web Text)

Max Activating Token Index: 985

Text #11

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7689. Min Act: -0.1700

Data Index: 6900731 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7529. Min Act: -0.1700

Data Index: 6580431 (Open Web Text)

Max Activating Token Index: 141

Text #13

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7505. Min Act: -0.1700

Data Index: 3930644 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7803. Min Act: -0.1700

Data Index: 3680406 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7655. Min Act: -0.1700

Data Index: 364319 (Open Web Text)

Max Activating Token Index: 562

Text #16

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7781. Min Act: -0.1700

Data Index: 1744761 (Open Web Text)

Max Activating Token Index: 785

Text #17

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7548. Min Act: -0.1700

Data Index: 7636217 (Open Web Text)

Max Activating Token Index: 333

Text #18

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7383. Min Act: -0.1700

Data Index: 1596493 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 3.9111. Min Range: -3.9111

Max Act: 3.7058. Min Act: -0.1700

Data Index: 4794791 (Open Web Text)

Max Activating Token Index: 762