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

Dataset: Open Web Text

Neuron 1866 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: 3.9832. Min Range: -3.9832

Max Act: 3.9832. Min Act: -0.1700

Data Index: 1691921 (Open Web Text)

Max Activating Token Index: 433

Text #1

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.9719. Min Act: -0.1700

Data Index: 5207917 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.9543. Min Act: -0.1700

Data Index: 5829547 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.9446. Min Act: -0.1700

Data Index: 4231659 (Open Web Text)

Max Activating Token Index: 579

Text #4

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.9358. Min Act: -0.1700

Data Index: 672155 (Open Web Text)

Max Activating Token Index: 969

Text #5

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.9007. Min Act: -0.1700

Data Index: 5533911 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.9004. Min Act: -0.1700

Data Index: 5916447 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.9268. Min Act: -0.1700

Data Index: 2940986 (Open Web Text)

Max Activating Token Index: 976

Text #8

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.8835. Min Act: -0.1700

Data Index: 1584780 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.9009. Min Act: -0.1700

Data Index: 4209411 (Open Web Text)

Max Activating Token Index: 854

Text #10

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.8630. Min Act: -0.1700

Data Index: 6822514 (Open Web Text)

Max Activating Token Index: 809

Text #11

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.8575. Min Act: -0.1700

Data Index: 7414297 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.8106. Min Act: -0.1700

Data Index: 3003549 (Open Web Text)

Max Activating Token Index: 248

Text #13

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.7993. Min Act: -0.1700

Data Index: 7656436 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.8144. Min Act: -0.1700

Data Index: 7291182 (Open Web Text)

Max Activating Token Index: 948

Text #15

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.8112. Min Act: -0.1700

Data Index: 7307017 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.7789. Min Act: -0.1700

Data Index: 2971729 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.7901. Min Act: -0.1700

Data Index: 5485074 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.7784. Min Act: -0.1700

Data Index: 4128458 (Open Web Text)

Max Activating Token Index: 281

Text #19

Max Range: 3.9832. Min Range: -3.9832

Max Act: 3.7890. Min Act: -0.1700

Data Index: 6693595 (Open Web Text)

Max Activating Token Index: 464