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

Dataset: Open Web Text

Neuron 1526 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: 5.2911. Min Range: -5.2911

Max Act: 5.2911. Min Act: -0.1700

Data Index: 1619521 (Open Web Text)

Max Activating Token Index: 817

Text #1

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.2467. Min Act: -0.1700

Data Index: 8746425 (Open Web Text)

Max Activating Token Index: 755

Text #2

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.2292. Min Act: -0.1700

Data Index: 4133960 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.2176. Min Act: -0.1700

Data Index: 5400892 (Open Web Text)

Max Activating Token Index: 134

Text #4

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1720. Min Act: -0.1700

Data Index: 8706621 (Open Web Text)

Max Activating Token Index: 212

Text #5

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1836. Min Act: -0.1700

Data Index: 4563344 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1889. Min Act: -0.1700

Data Index: 2765352 (Open Web Text)

Max Activating Token Index: 800

Text #7

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1624. Min Act: -0.1700

Data Index: 7059413 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1589. Min Act: -0.1700

Data Index: 5635915 (Open Web Text)

Max Activating Token Index: 896

Text #9

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1321. Min Act: -0.1700

Data Index: 6276106 (Open Web Text)

Max Activating Token Index: 806

Text #10

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1655. Min Act: -0.1700

Data Index: 164801 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1781. Min Act: -0.1700

Data Index: 7405646 (Open Web Text)

Max Activating Token Index: 331

Text #12

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1077. Min Act: -0.1700

Data Index: 6025676 (Open Web Text)

Max Activating Token Index: 287

Text #13

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.0908. Min Act: -0.1700

Data Index: 7427020 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1286. Min Act: -0.1700

Data Index: 4238372 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1299. Min Act: -0.1700

Data Index: 1083839 (Open Web Text)

Max Activating Token Index: 855

Text #16

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1114. Min Act: -0.1700

Data Index: 3305946 (Open Web Text)

Max Activating Token Index: 822

Text #17

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1174. Min Act: -0.1700

Data Index: 2795920 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1197. Min Act: -0.1700

Data Index: 6895153 (Open Web Text)

Max Activating Token Index: 901

Text #19

Max Range: 5.2911. Min Range: -5.2911

Max Act: 5.1371. Min Act: -0.1700

Data Index: 6174724 (Open Web Text)

Max Activating Token Index: 404