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

Dataset: Open Web Text

Neuron 211 in Layer 6

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: 4.1636. Min Range: -4.1636

Max Act: 4.1636. Min Act: -0.1700

Data Index: 5459605 (Open Web Text)

Max Activating Token Index: 893

Text #1

Max Range: 4.1636. Min Range: -4.1636

Max Act: 4.0680. Min Act: -0.1700

Data Index: 4954325 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 4.1636. Min Range: -4.1636

Max Act: 4.0300. Min Act: -0.1700

Data Index: 6695938 (Open Web Text)

Max Activating Token Index: 483

Text #3

Max Range: 4.1636. Min Range: -4.1636

Max Act: 4.0164. Min Act: -0.1700

Data Index: 6527721 (Open Web Text)

Max Activating Token Index: 490

Text #4

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9984. Min Act: -0.1700

Data Index: 7850024 (Open Web Text)

Max Activating Token Index: 744

Text #5

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9752. Min Act: -0.1700

Data Index: 879877 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9885. Min Act: -0.1700

Data Index: 7493492 (Open Web Text)

Max Activating Token Index: 512

Text #7

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9417. Min Act: -0.1700

Data Index: 4422972 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9532. Min Act: -0.1700

Data Index: 6150595 (Open Web Text)

Max Activating Token Index: 295

Text #9

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9713. Min Act: -0.1700

Data Index: 4473276 (Open Web Text)

Max Activating Token Index: 770

Text #10

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9132. Min Act: -0.1700

Data Index: 2613445 (Open Web Text)

Max Activating Token Index: 934

Text #11

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9176. Min Act: -0.1700

Data Index: 945909 (Open Web Text)

Max Activating Token Index: 147

Text #12

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9376. Min Act: -0.1700

Data Index: 373174 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9422. Min Act: -0.1700

Data Index: 5651899 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9175. Min Act: -0.1700

Data Index: 5462148 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9201. Min Act: -0.1700

Data Index: 6943250 (Open Web Text)

Max Activating Token Index: 310

Text #16

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9067. Min Act: -0.1700

Data Index: 5904764 (Open Web Text)

Max Activating Token Index: 301

Text #17

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.8785. Min Act: -0.1700

Data Index: 6086280 (Open Web Text)

Max Activating Token Index: 914

Text #18

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.9037. Min Act: -0.1700

Data Index: 2144344 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.8839. Min Act: -0.1700

Data Index: 2076559 (Open Web Text)

Max Activating Token Index: 638