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

Dataset: Open Web Text

Neuron 2760 in Layer 1

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: 1.1695. Min Range: -1.1695

Max Act: 1.1695. Min Act: -0.1357

Data Index: 1355974 (Open Web Text)

Max Activating Token Index: 258

Text #1

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1504. Min Act: -0.1698

Data Index: 4627250 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1331. Min Act: -0.1700

Data Index: 4333541 (Open Web Text)

Max Activating Token Index: 366

Text #3

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1315. Min Act: -0.1683

Data Index: 8458592 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1341. Min Act: -0.1697

Data Index: 1064646 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1224. Min Act: -0.1658

Data Index: 8347333 (Open Web Text)

Max Activating Token Index: 632

Text #6

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1143. Min Act: -0.1625

Data Index: 6038392 (Open Web Text)

Max Activating Token Index: 188

Text #7

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1081. Min Act: -0.1690

Data Index: 3007030 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0930. Min Act: -0.1695

Data Index: 6532823 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0984. Min Act: -0.1696

Data Index: 7771715 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0926. Min Act: -0.1698

Data Index: 3613243 (Open Web Text)

Max Activating Token Index: 956

Text #11

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1012. Min Act: -0.1660

Data Index: 1661042 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0893. Min Act: -0.1700

Data Index: 2563277 (Open Web Text)

Max Activating Token Index: 171

Text #13

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0894. Min Act: -0.1700

Data Index: 4226326 (Open Web Text)

Max Activating Token Index: 52

Text #14

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0952. Min Act: -0.1697

Data Index: 4868237 (Open Web Text)

Max Activating Token Index: 916

Text #15

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0892. Min Act: -0.1678

Data Index: 5087296 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0909. Min Act: -0.1378

Data Index: 8157730 (Open Web Text)

Max Activating Token Index: 196

Text #17

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0925. Min Act: -0.1641

Data Index: 3686179 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0910. Min Act: -0.1700

Data Index: 6348297 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0904. Min Act: -0.1696

Data Index: 6173335 (Open Web Text)

Max Activating Token Index: 936