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

Dataset: Open Web Text

Neuron 1888 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: 2.1368. Min Range: -2.1368

Max Act: 2.1368. Min Act: -0.1700

Data Index: 1865679 (Open Web Text)

Max Activating Token Index: 901

Text #1

Max Range: 2.1368. Min Range: -2.1368

Max Act: 2.0323. Min Act: -0.1700

Data Index: 5106670 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 2.1368. Min Range: -2.1368

Max Act: 2.0033. Min Act: -0.1700

Data Index: 1736645 (Open Web Text)

Max Activating Token Index: 355

Text #3

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9915. Min Act: -0.1700

Data Index: 1108669 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9435. Min Act: -0.1700

Data Index: 4899869 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9336. Min Act: -0.1700

Data Index: 8703755 (Open Web Text)

Max Activating Token Index: 711

Text #6

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9450. Min Act: -0.1700

Data Index: 5258680 (Open Web Text)

Max Activating Token Index: 858

Text #7

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9651. Min Act: -0.1700

Data Index: 4289684 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9441. Min Act: -0.1700

Data Index: 7183410 (Open Web Text)

Max Activating Token Index: 88

Text #9

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9736. Min Act: -0.1700

Data Index: 2014948 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9409. Min Act: -0.1700

Data Index: 7581373 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9056. Min Act: -0.1700

Data Index: 2837391 (Open Web Text)

Max Activating Token Index: 665

Text #12

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9088. Min Act: -0.1700

Data Index: 2071573 (Open Web Text)

Max Activating Token Index: 182

Text #13

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9098. Min Act: -0.1700

Data Index: 2572307 (Open Web Text)

Max Activating Token Index: 449

Text #14

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.9103. Min Act: -0.1700

Data Index: 8016037 (Open Web Text)

Max Activating Token Index: 201

Text #15

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.8691. Min Act: -0.1700

Data Index: 983958 (Open Web Text)

Max Activating Token Index: 298

Text #16

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.8889. Min Act: -0.1700

Data Index: 4187021 (Open Web Text)

Max Activating Token Index: 388

Text #17

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.8636. Min Act: -0.1700

Data Index: 8822468 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.8665. Min Act: -0.1700

Data Index: 3737394 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.1368. Min Range: -2.1368

Max Act: 1.8783. Min Act: -0.1700

Data Index: 5346248 (Open Web Text)

Max Activating Token Index: 447