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

Dataset: Open Web Text

Neuron 912 in Layer 0

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: 3.0467. Min Range: -3.0467

Max Act: 3.0452. Min Act: -0.1700

Data Index: 1907711 (Open Web Text)

Max Activating Token Index: 836

Text #1

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0414. Min Act: -0.1700

Data Index: 5844079 (Open Web Text)

Max Activating Token Index: 819

Text #2

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0467. Min Act: -0.1700

Data Index: 1628837 (Open Web Text)

Max Activating Token Index: 832

Text #3

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0428. Min Act: -0.1700

Data Index: 8818943 (Open Web Text)

Max Activating Token Index: 836

Text #4

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0416. Min Act: -0.1700

Data Index: 3951653 (Open Web Text)

Max Activating Token Index: 835

Text #5

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0241. Min Act: -0.1700

Data Index: 5543306 (Open Web Text)

Max Activating Token Index: 832

Text #6

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0076. Min Act: -0.1700

Data Index: 4689090 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0145. Min Act: -0.1700

Data Index: 2649860 (Open Web Text)

Max Activating Token Index: 836

Text #8

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0182. Min Act: -0.1700

Data Index: 4193168 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0260. Min Act: -0.1700

Data Index: 2378280 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0180. Min Act: -0.1700

Data Index: 1213624 (Open Web Text)

Max Activating Token Index: 835

Text #11

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0106. Min Act: -0.1700

Data Index: 7428729 (Open Web Text)

Max Activating Token Index: 832

Text #12

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0114. Min Act: -0.1700

Data Index: 6103908 (Open Web Text)

Max Activating Token Index: 845

Text #13

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0059. Min Act: -0.1700

Data Index: 5762342 (Open Web Text)

Max Activating Token Index: 837

Text #14

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0252. Min Act: -0.1700

Data Index: 4816552 (Open Web Text)

Max Activating Token Index: 833

Text #15

Max Range: 3.0467. Min Range: -3.0467

Max Act: 2.9895. Min Act: -0.1700

Data Index: 3045010 (Open Web Text)

Max Activating Token Index: 835

Text #16

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0093. Min Act: -0.1697

Data Index: 2438356 (Open Web Text)

Max Activating Token Index: 842

Text #17

Max Range: 3.0467. Min Range: -3.0467

Max Act: 3.0023. Min Act: -0.1700

Data Index: 137609 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 3.0467. Min Range: -3.0467

Max Act: 2.9939. Min Act: -0.1700

Data Index: 4214479 (Open Web Text)

Max Activating Token Index: 827

Text #19

Max Range: 3.0467. Min Range: -3.0467

Max Act: 2.9956. Min Act: -0.1700

Data Index: 4760297 (Open Web Text)

Max Activating Token Index: 825