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

Dataset: Open Web Text

Neuron 2220 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: 3.8976. Min Range: -3.8976

Max Act: 3.8976. Min Act: -0.1700

Data Index: 379716 (Open Web Text)

Max Activating Token Index: 690

Text #1

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.8335. Min Act: -0.1700

Data Index: 2320245 (Open Web Text)

Max Activating Token Index: 590

Text #2

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.8180. Min Act: -0.1700

Data Index: 3247069 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.7720. Min Act: -0.1700

Data Index: 3981899 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.7840. Min Act: -0.1700

Data Index: 58553 (Open Web Text)

Max Activating Token Index: 702

Text #5

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.7608. Min Act: -0.1700

Data Index: 5233891 (Open Web Text)

Max Activating Token Index: 302

Text #6

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.7561. Min Act: -0.1700

Data Index: 3039026 (Open Web Text)

Max Activating Token Index: 237

Text #7

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1847738 (Open Web Text)

Max Activating Token Index: 685

Text #8

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.7047. Min Act: -0.1700

Data Index: 6421666 (Open Web Text)

Max Activating Token Index: 388

Text #9

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6978. Min Act: -0.1700

Data Index: 2989977 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6947. Min Act: -0.1700

Data Index: 5271473 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6849. Min Act: -0.1700

Data Index: 2465396 (Open Web Text)

Max Activating Token Index: 795

Text #12

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6852. Min Act: -0.1700

Data Index: 7121643 (Open Web Text)

Max Activating Token Index: 289

Text #13

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6688. Min Act: -0.1700

Data Index: 2365524 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6655. Min Act: -0.1700

Data Index: 1008249 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6710. Min Act: -0.1700

Data Index: 5744696 (Open Web Text)

Max Activating Token Index: 789

Text #16

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6804. Min Act: -0.1700

Data Index: 3332756 (Open Web Text)

Max Activating Token Index: 360

Text #17

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6645. Min Act: -0.1700

Data Index: 2431935 (Open Web Text)

Max Activating Token Index: 216

Text #18

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6605. Min Act: -0.1700

Data Index: 7447124 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 3.8976. Min Range: -3.8976

Max Act: 3.6658. Min Act: -0.1700

Data Index: 2068042 (Open Web Text)

Max Activating Token Index: 187