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

Dataset: Open Web Text

Neuron 2021 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: 4.0875. Min Range: -4.0875

Max Act: 4.0875. Min Act: -0.1700

Data Index: 2341140 (Open Web Text)

Max Activating Token Index: 319

Text #1

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.9874. Min Act: -0.1700

Data Index: 4694909 (Open Web Text)

Max Activating Token Index: 850

Text #2

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.8722. Min Act: -0.1700

Data Index: 4644095 (Open Web Text)

Max Activating Token Index: 529

Text #3

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.8751. Min Act: -0.1700

Data Index: 8570303 (Open Web Text)

Max Activating Token Index: 380

Text #4

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.8631. Min Act: -0.1700

Data Index: 50803 (Open Web Text)

Max Activating Token Index: 246

Text #5

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7707. Min Act: -0.1700

Data Index: 6887664 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.8287. Min Act: -0.1700

Data Index: 8014754 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.8395. Min Act: -0.1700

Data Index: 5478935 (Open Web Text)

Max Activating Token Index: 839

Text #8

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.8262. Min Act: -0.1700

Data Index: 6365590 (Open Web Text)

Max Activating Token Index: 278

Text #9

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.8010. Min Act: -0.1700

Data Index: 6005289 (Open Web Text)

Max Activating Token Index: 804

Text #10

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7480. Min Act: -0.1700

Data Index: 1699100 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7657. Min Act: -0.1700

Data Index: 1313938 (Open Web Text)

Max Activating Token Index: 273

Text #12

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7684. Min Act: -0.1700

Data Index: 71310 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7655. Min Act: -0.1700

Data Index: 8215716 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7533. Min Act: -0.1700

Data Index: 3853823 (Open Web Text)

Max Activating Token Index: 685

Text #15

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7501. Min Act: -0.1700

Data Index: 7202716 (Open Web Text)

Max Activating Token Index: 724

Text #16

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7270. Min Act: -0.1700

Data Index: 150745 (Open Web Text)

Max Activating Token Index: 229

Text #17

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1850718 (Open Web Text)

Max Activating Token Index: 279

Text #18

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7185. Min Act: -0.1700

Data Index: 5339687 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.6714. Min Act: -0.1700

Data Index: 5469152 (Open Web Text)

Max Activating Token Index: 838