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

Dataset: Open Web Text

Neuron 1112 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: 4.9792. Min Range: -4.9792

Max Act: 4.9792. Min Act: -0.1700

Data Index: 6131193 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.9472. Min Act: -0.1700

Data Index: 4647715 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8798. Min Act: -0.1700

Data Index: 6624398 (Open Web Text)

Max Activating Token Index: 389

Text #3

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8350. Min Act: -0.1700

Data Index: 2536598 (Open Web Text)

Max Activating Token Index: 254

Text #4

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8568. Min Act: -0.1700

Data Index: 1237040 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8282. Min Act: -0.1700

Data Index: 5547012 (Open Web Text)

Max Activating Token Index: 38

Text #6

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8180. Min Act: -0.1700

Data Index: 3617428 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8545. Min Act: -0.1700

Data Index: 1100737 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7803. Min Act: -0.1700

Data Index: 7329555 (Open Web Text)

Max Activating Token Index: 534

Text #9

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8081. Min Act: -0.1700

Data Index: 5928225 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8247. Min Act: -0.1700

Data Index: 744376 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7762. Min Act: -0.1700

Data Index: 6950606 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7755. Min Act: -0.1700

Data Index: 6920006 (Open Web Text)

Max Activating Token Index: 623

Text #13

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7894. Min Act: -0.1700

Data Index: 5161758 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7899. Min Act: -0.1700

Data Index: 6584825 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7925. Min Act: -0.1700

Data Index: 6569464 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8000. Min Act: -0.1700

Data Index: 6289277 (Open Web Text)

Max Activating Token Index: 994

Text #17

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7987. Min Act: -0.1700

Data Index: 2973871 (Open Web Text)

Max Activating Token Index: 419

Text #18

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.7812. Min Act: -0.1700

Data Index: 2215701 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 4.9792. Min Range: -4.9792

Max Act: 4.8191. Min Act: -0.1700

Data Index: 1451383 (Open Web Text)

Max Activating Token Index: 1023