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

Dataset: Open Web Text

Neuron 75 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: 3.5656. Min Range: -3.5656

Max Act: 3.5584. Min Act: -0.1700

Data Index: 4923182 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.5656. Min Act: -0.1700

Data Index: 8509737 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.5142. Min Act: -0.1700

Data Index: 6280391 (Open Web Text)

Max Activating Token Index: 789

Text #3

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4590. Min Act: -0.1700

Data Index: 2840541 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4639. Min Act: -0.1700

Data Index: 8724486 (Open Web Text)

Max Activating Token Index: 380

Text #5

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4486. Min Act: -0.1700

Data Index: 6434596 (Open Web Text)

Max Activating Token Index: 403

Text #6

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3773. Min Act: -0.1700

Data Index: 7146417 (Open Web Text)

Max Activating Token Index: 255

Text #7

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3828. Min Act: -0.1700

Data Index: 4923186 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3815. Min Act: -0.1700

Data Index: 1243949 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3493. Min Act: -0.1700

Data Index: 4048471 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3496. Min Act: -0.1700

Data Index: 4782004 (Open Web Text)

Max Activating Token Index: 496

Text #11

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3299. Min Act: -0.1700

Data Index: 1581240 (Open Web Text)

Max Activating Token Index: 949

Text #12

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3032. Min Act: -0.1700

Data Index: 1760497 (Open Web Text)

Max Activating Token Index: 799

Text #13

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3142. Min Act: -0.1700

Data Index: 45498 (Open Web Text)

Max Activating Token Index: 316

Text #14

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.2942. Min Act: -0.1700

Data Index: 4011150 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.2746. Min Act: -0.1700

Data Index: 4115608 (Open Web Text)

Max Activating Token Index: 889

Text #16

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.2718. Min Act: -0.1700

Data Index: 730719 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.2726. Min Act: -0.1700

Data Index: 4185209 (Open Web Text)

Max Activating Token Index: 207

Text #18

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.2528. Min Act: -0.1700

Data Index: 6890249 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.2493. Min Act: -0.1700

Data Index: 6031929 (Open Web Text)

Max Activating Token Index: 5