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

Dataset: Open Web Text

Neuron 2915 in Layer 4

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: 2.9419. Min Range: -2.9419

Max Act: 2.9419. Min Act: -0.1700

Data Index: 210818 (Open Web Text)

Max Activating Token Index: 739

Text #1

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.8776. Min Act: -0.1700

Data Index: 6045552 (Open Web Text)

Max Activating Token Index: 672

Text #2

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.8255. Min Act: -0.1700

Data Index: 6045548 (Open Web Text)

Max Activating Token Index: 208

Text #3

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7827. Min Act: -0.1700

Data Index: 310478 (Open Web Text)

Max Activating Token Index: 655

Text #4

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7595. Min Act: -0.1700

Data Index: 310476 (Open Web Text)

Max Activating Token Index: 784

Text #5

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.8139. Min Act: -0.1700

Data Index: 6095024 (Open Web Text)

Max Activating Token Index: 780

Text #6

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7831. Min Act: -0.1700

Data Index: 310467 (Open Web Text)

Max Activating Token Index: 258

Text #7

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7340. Min Act: -0.1700

Data Index: 4431649 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7377. Min Act: -0.1700

Data Index: 310474 (Open Web Text)

Max Activating Token Index: 540

Text #9

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7328. Min Act: -0.1700

Data Index: 4431645 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7309. Min Act: -0.1700

Data Index: 4431652 (Open Web Text)

Max Activating Token Index: 370

Text #11

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7231. Min Act: -0.1700

Data Index: 310466 (Open Web Text)

Max Activating Token Index: 783

Text #12

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7203. Min Act: -0.1700

Data Index: 4431639 (Open Web Text)

Max Activating Token Index: 465

Text #13

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.6929. Min Act: -0.1700

Data Index: 7080287 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.7082. Min Act: -0.1700

Data Index: 6045553 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.6688. Min Act: -0.1700

Data Index: 5037732 (Open Web Text)

Max Activating Token Index: 499

Text #16

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.6783. Min Act: -0.1700

Data Index: 8438880 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.6773. Min Act: -0.1700

Data Index: 2505738 (Open Web Text)

Max Activating Token Index: 804

Text #18

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.6419. Min Act: -0.1700

Data Index: 3913323 (Open Web Text)

Max Activating Token Index: 541

Text #19

Max Range: 2.9419. Min Range: -2.9419

Max Act: 2.6366. Min Act: -0.1700

Data Index: 310465 (Open Web Text)

Max Activating Token Index: 98