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

Dataset: Open Web Text

Neuron 2712 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: 1.9912. Min Range: -1.9912

Max Act: 1.9912. Min Act: -0.1700

Data Index: 6547405 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.9502. Min Act: -0.1700

Data Index: 6079113 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.8890. Min Act: -0.1700

Data Index: 5938840 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.8797. Min Act: -0.1700

Data Index: 1046131 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.8516. Min Act: -0.1700

Data Index: 5663476 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7994. Min Act: -0.1700

Data Index: 5468621 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7904. Min Act: -0.1700

Data Index: 4286663 (Open Web Text)

Max Activating Token Index: 206

Text #7

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7795. Min Act: -0.1700

Data Index: 6338385 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7631. Min Act: -0.1700

Data Index: 7982780 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7168. Min Act: -0.1700

Data Index: 7810922 (Open Web Text)

Max Activating Token Index: 599

Text #10

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7241. Min Act: -0.1700

Data Index: 3835764 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7244. Min Act: -0.1700

Data Index: 6149953 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7048. Min Act: -0.1700

Data Index: 5381877 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.6865. Min Act: -0.1700

Data Index: 8772506 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.6791. Min Act: -0.1700

Data Index: 3661879 (Open Web Text)

Max Activating Token Index: 357

Text #15

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.6568. Min Act: -0.1700

Data Index: 5969383 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.7275. Min Act: -0.1700

Data Index: 7306677 (Open Web Text)

Max Activating Token Index: 664

Text #17

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.6917. Min Act: -0.1700

Data Index: 455660 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.6786. Min Act: -0.1700

Data Index: 7263898 (Open Web Text)

Max Activating Token Index: 951

Text #19

Max Range: 1.9912. Min Range: -1.9912

Max Act: 1.6626. Min Act: -0.1700

Data Index: 7806332 (Open Web Text)

Max Activating Token Index: 13