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

Dataset: Open Web Text

Neuron 571 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: 7.1821. Min Range: -7.1821

Max Act: 7.1821. Min Act: -0.1700

Data Index: 118684 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.9864. Min Act: -0.1700

Data Index: 118672 (Open Web Text)

Max Activating Token Index: 702

Text #2

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.7975. Min Act: -0.1700

Data Index: 791270 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.7686. Min Act: -0.1700

Data Index: 2376189 (Open Web Text)

Max Activating Token Index: 660

Text #4

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.7445. Min Act: -0.1700

Data Index: 7970047 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.7353. Min Act: -0.1700

Data Index: 319352 (Open Web Text)

Max Activating Token Index: 141

Text #6

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.7127. Min Act: -0.1700

Data Index: 7492446 (Open Web Text)

Max Activating Token Index: 112

Text #7

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6875. Min Act: -0.1700

Data Index: 6378882 (Open Web Text)

Max Activating Token Index: 305

Text #8

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.7205. Min Act: -0.1700

Data Index: 2057339 (Open Web Text)

Max Activating Token Index: 744

Text #9

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6788. Min Act: -0.1700

Data Index: 1225465 (Open Web Text)

Max Activating Token Index: 518

Text #10

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6692. Min Act: -0.1700

Data Index: 6020006 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6945. Min Act: -0.1700

Data Index: 8699408 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6559. Min Act: -0.1700

Data Index: 5679397 (Open Web Text)

Max Activating Token Index: 99

Text #13

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6153. Min Act: -0.1700

Data Index: 4713372 (Open Web Text)

Max Activating Token Index: 243

Text #14

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6292. Min Act: -0.1700

Data Index: 2809806 (Open Web Text)

Max Activating Token Index: 699

Text #15

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6351. Min Act: -0.1700

Data Index: 8822379 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6001. Min Act: -0.1700

Data Index: 36626 (Open Web Text)

Max Activating Token Index: 465

Text #17

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6071. Min Act: -0.1700

Data Index: 4824566 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6155. Min Act: -0.1700

Data Index: 8549656 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 7.1821. Min Range: -7.1821

Max Act: 6.6205. Min Act: -0.1700

Data Index: 3370524 (Open Web Text)

Max Activating Token Index: 628