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

Dataset: Open Web Text

Neuron 1984 in Layer 5

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: 3.1769. Min Range: -3.1769

Max Act: 3.1769. Min Act: -0.1700

Data Index: 5926134 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.1455. Min Act: -0.1700

Data Index: 4037488 (Open Web Text)

Max Activating Token Index: 992

Text #2

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0783. Min Act: -0.1700

Data Index: 5755447 (Open Web Text)

Max Activating Token Index: 903

Text #3

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0614. Min Act: -0.1700

Data Index: 3126030 (Open Web Text)

Max Activating Token Index: 449

Text #4

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0999. Min Act: -0.1700

Data Index: 6172962 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0888. Min Act: -0.1700

Data Index: 5817409 (Open Web Text)

Max Activating Token Index: 296

Text #6

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0937. Min Act: -0.1700

Data Index: 2933465 (Open Web Text)

Max Activating Token Index: 799

Text #7

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0880. Min Act: -0.1700

Data Index: 6425992 (Open Web Text)

Max Activating Token Index: 435

Text #8

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0386. Min Act: -0.1700

Data Index: 6662713 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0674. Min Act: -0.1700

Data Index: 1331490 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9992. Min Act: -0.1700

Data Index: 1320950 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9638. Min Act: -0.1700

Data Index: 4391297 (Open Web Text)

Max Activating Token Index: 729

Text #12

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0430. Min Act: -0.1700

Data Index: 6678937 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0106. Min Act: -0.1700

Data Index: 7171728 (Open Web Text)

Max Activating Token Index: 968

Text #14

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0254. Min Act: -0.1700

Data Index: 229006 (Open Web Text)

Max Activating Token Index: 925

Text #15

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0336. Min Act: -0.1700

Data Index: 6557977 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0229. Min Act: -0.1700

Data Index: 6172179 (Open Web Text)

Max Activating Token Index: 214

Text #17

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9932. Min Act: -0.1700

Data Index: 3725581 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9920. Min Act: -0.1700

Data Index: 16103 (Open Web Text)

Max Activating Token Index: 269

Text #19

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9937. Min Act: -0.1700

Data Index: 2514238 (Open Web Text)

Max Activating Token Index: 872