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

Dataset: Open Web Text

Neuron 715 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: 3.6882. Min Range: -3.6882

Max Act: 3.6826. Min Act: -0.1700

Data Index: 289376 (Open Web Text)

Max Activating Token Index: 57

Text #1

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.6882. Min Act: -0.1700

Data Index: 6096055 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.6297. Min Act: -0.1700

Data Index: 5389401 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.6168. Min Act: -0.1700

Data Index: 5456485 (Open Web Text)

Max Activating Token Index: 515

Text #4

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.6073. Min Act: -0.1700

Data Index: 2282371 (Open Web Text)

Max Activating Token Index: 880

Text #5

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.6058. Min Act: -0.1700

Data Index: 1733771 (Open Web Text)

Max Activating Token Index: 449

Text #6

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5373. Min Act: -0.1700

Data Index: 6746612 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5285. Min Act: -0.1700

Data Index: 5622078 (Open Web Text)

Max Activating Token Index: 777

Text #8

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5359. Min Act: -0.1700

Data Index: 192518 (Open Web Text)

Max Activating Token Index: 377

Text #9

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5268. Min Act: -0.1700

Data Index: 8611634 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5345. Min Act: -0.1700

Data Index: 3226320 (Open Web Text)

Max Activating Token Index: 863

Text #11

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5246. Min Act: -0.1700

Data Index: 614430 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5076. Min Act: -0.1700

Data Index: 5727298 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5082. Min Act: -0.1700

Data Index: 1418918 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.4926. Min Act: -0.1700

Data Index: 38689 (Open Web Text)

Max Activating Token Index: 103

Text #15

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.4761. Min Act: -0.1700

Data Index: 8230116 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.5171. Min Act: -0.1700

Data Index: 7867894 (Open Web Text)

Max Activating Token Index: 865

Text #17

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.4712. Min Act: -0.1700

Data Index: 38687 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.4689. Min Act: -0.1700

Data Index: 5135307 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 3.6882. Min Range: -3.6882

Max Act: 3.4662. Min Act: -0.1700

Data Index: 7367016 (Open Web Text)

Max Activating Token Index: 48