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

Dataset: Open Web Text

Neuron 1243 in Layer 1

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: 1.7564. Min Range: -1.7564

Max Act: 1.7564. Min Act: -0.1700

Data Index: 4479245 (Open Web Text)

Max Activating Token Index: 488

Text #1

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.7306. Min Act: -0.1700

Data Index: 1030721 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.7007. Min Act: -0.1700

Data Index: 2379981 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6863. Min Act: -0.1700

Data Index: 6716477 (Open Web Text)

Max Activating Token Index: 635

Text #4

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6896. Min Act: -0.1700

Data Index: 2577460 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6937. Min Act: -0.1700

Data Index: 5523059 (Open Web Text)

Max Activating Token Index: 548

Text #6

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6791. Min Act: -0.1700

Data Index: 8378091 (Open Web Text)

Max Activating Token Index: 882

Text #7

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6721. Min Act: -0.1700

Data Index: 8774037 (Open Web Text)

Max Activating Token Index: 218

Text #8

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6763. Min Act: -0.1700

Data Index: 5411471 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6694. Min Act: -0.1700

Data Index: 464188 (Open Web Text)

Max Activating Token Index: 458

Text #10

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6691. Min Act: -0.1700

Data Index: 5870796 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6559. Min Act: -0.1700

Data Index: 370091 (Open Web Text)

Max Activating Token Index: 499

Text #12

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6514. Min Act: -0.1700

Data Index: 6024099 (Open Web Text)

Max Activating Token Index: 440

Text #13

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6562. Min Act: -0.1700

Data Index: 8534600 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6649. Min Act: -0.1700

Data Index: 1493849 (Open Web Text)

Max Activating Token Index: 768

Text #15

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6654. Min Act: -0.1700

Data Index: 5534254 (Open Web Text)

Max Activating Token Index: 399

Text #16

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6651. Min Act: -0.1700

Data Index: 7023100 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6510. Min Act: -0.1700

Data Index: 3664031 (Open Web Text)

Max Activating Token Index: 266

Text #18

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6630. Min Act: -0.1700

Data Index: 3153295 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 1.7564. Min Range: -1.7564

Max Act: 1.6329. Min Act: -0.1700

Data Index: 3067307 (Open Web Text)

Max Activating Token Index: 549