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

Dataset: Open Web Text

Neuron 68 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: 4.2911. Min Range: -4.2911

Max Act: 4.2911. Min Act: -0.1700

Data Index: 5497714 (Open Web Text)

Max Activating Token Index: 734

Text #1

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2604. Min Act: -0.1700

Data Index: 3297426 (Open Web Text)

Max Activating Token Index: 881

Text #2

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2706. Min Act: -0.1700

Data Index: 1198822 (Open Web Text)

Max Activating Token Index: 932

Text #3

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2509. Min Act: -0.1700

Data Index: 220383 (Open Web Text)

Max Activating Token Index: 745

Text #4

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2719. Min Act: -0.1700

Data Index: 7855370 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2453. Min Act: -0.1700

Data Index: 5337095 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2211. Min Act: -0.1700

Data Index: 5335852 (Open Web Text)

Max Activating Token Index: 862

Text #7

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2254. Min Act: -0.1700

Data Index: 1287999 (Open Web Text)

Max Activating Token Index: 995

Text #8

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2101. Min Act: -0.1700

Data Index: 6997621 (Open Web Text)

Max Activating Token Index: 606

Text #9

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2145. Min Act: -0.1700

Data Index: 4963584 (Open Web Text)

Max Activating Token Index: 498

Text #10

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1750. Min Act: -0.1700

Data Index: 7581164 (Open Web Text)

Max Activating Token Index: 727

Text #11

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2077. Min Act: -0.1700

Data Index: 1714310 (Open Web Text)

Max Activating Token Index: 502

Text #12

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1734. Min Act: -0.1700

Data Index: 6452495 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1845. Min Act: -0.1700

Data Index: 8731732 (Open Web Text)

Max Activating Token Index: 988

Text #14

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1635. Min Act: -0.1700

Data Index: 5807960 (Open Web Text)

Max Activating Token Index: 581

Text #15

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1466. Min Act: -0.1700

Data Index: 4227856 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1763. Min Act: -0.1700

Data Index: 5384573 (Open Web Text)

Max Activating Token Index: 596

Text #17

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1723. Min Act: -0.1700

Data Index: 4194644 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1856. Min Act: -0.1700

Data Index: 747732 (Open Web Text)

Max Activating Token Index: 419

Text #19

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1307. Min Act: -0.1700

Data Index: 2718220 (Open Web Text)

Max Activating Token Index: 741