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

Dataset: Open Web Text

Neuron 254 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: 3.8667. Min Range: -3.8667

Max Act: 3.8444. Min Act: -0.1700

Data Index: 2565890 (Open Web Text)

Max Activating Token Index: 964

Text #1

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.8514. Min Act: -0.1700

Data Index: 7630808 (Open Web Text)

Max Activating Token Index: 109

Text #2

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.8418. Min Act: -0.1700

Data Index: 4953250 (Open Web Text)

Max Activating Token Index: 398

Text #3

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.8667. Min Act: -0.1700

Data Index: 8335547 (Open Web Text)

Max Activating Token Index: 136

Text #4

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.8642. Min Act: -0.1700

Data Index: 8560930 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.8245. Min Act: -0.1700

Data Index: 7675435 (Open Web Text)

Max Activating Token Index: 241

Text #6

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.8075. Min Act: -0.1700

Data Index: 267627 (Open Web Text)

Max Activating Token Index: 151

Text #7

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7901. Min Act: -0.1700

Data Index: 679948 (Open Web Text)

Max Activating Token Index: 361

Text #8

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7754. Min Act: -0.1700

Data Index: 14553 (Open Web Text)

Max Activating Token Index: 568

Text #9

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7776. Min Act: -0.1700

Data Index: 2313071 (Open Web Text)

Max Activating Token Index: 315

Text #10

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7900. Min Act: -0.1700

Data Index: 2921799 (Open Web Text)

Max Activating Token Index: 64

Text #11

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7716. Min Act: -0.1700

Data Index: 3765829 (Open Web Text)

Max Activating Token Index: 973

Text #12

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7595. Min Act: -0.1700

Data Index: 4289619 (Open Web Text)

Max Activating Token Index: 490

Text #13

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7771. Min Act: -0.1700

Data Index: 2137588 (Open Web Text)

Max Activating Token Index: 348

Text #14

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7912. Min Act: -0.1700

Data Index: 7795981 (Open Web Text)

Max Activating Token Index: 386

Text #15

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7405. Min Act: -0.1700

Data Index: 3195087 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7072. Min Act: -0.1700

Data Index: 6525826 (Open Web Text)

Max Activating Token Index: 738

Text #17

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7248. Min Act: -0.1700

Data Index: 7517549 (Open Web Text)

Max Activating Token Index: 850

Text #18

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7318. Min Act: -0.1700

Data Index: 3102253 (Open Web Text)

Max Activating Token Index: 826

Text #19

Max Range: 3.8667. Min Range: -3.8667

Max Act: 3.7050. Min Act: -0.1700

Data Index: 1032798 (Open Web Text)

Max Activating Token Index: 218