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

Dataset: Open Web Text

Neuron 229 in Layer 1

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: 1.8508. Min Range: -1.8508

Max Act: 1.8508. Min Act: -0.1700

Data Index: 8239172 (Open Web Text)

Max Activating Token Index: 86

Text #1

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.8381. Min Act: -0.1698

Data Index: 6887319 (Open Web Text)

Max Activating Token Index: 197

Text #2

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.8116. Min Act: -0.1699

Data Index: 8061955 (Open Web Text)

Max Activating Token Index: 185

Text #3

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7993. Min Act: -0.1700

Data Index: 360684 (Open Web Text)

Max Activating Token Index: 177

Text #4

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.8058. Min Act: -0.1700

Data Index: 2857103 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.8032. Min Act: -0.1699

Data Index: 5859515 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7856. Min Act: -0.1700

Data Index: 5643853 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7833. Min Act: -0.1700

Data Index: 692228 (Open Web Text)

Max Activating Token Index: 168

Text #8

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7744. Min Act: -0.1700

Data Index: 7803351 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7764. Min Act: -0.1700

Data Index: 1833479 (Open Web Text)

Max Activating Token Index: 756

Text #10

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7683. Min Act: -0.1689

Data Index: 7624559 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7658. Min Act: -0.1697

Data Index: 8355113 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7692. Min Act: -0.1700

Data Index: 3079446 (Open Web Text)

Max Activating Token Index: 91

Text #13

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7715. Min Act: -0.1700

Data Index: 183184 (Open Web Text)

Max Activating Token Index: 90

Text #14

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7615. Min Act: -0.1700

Data Index: 2374973 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7603. Min Act: -0.1679

Data Index: 2523191 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7662. Min Act: -0.1700

Data Index: 3278494 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7477. Min Act: -0.1677

Data Index: 762619 (Open Web Text)

Max Activating Token Index: 160

Text #18

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7504. Min Act: -0.1700

Data Index: 5984579 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 1.8508. Min Range: -1.8508

Max Act: 1.7535. Min Act: -0.1698

Data Index: 1145978 (Open Web Text)

Max Activating Token Index: 530