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

Dataset: Open Web Text

Neuron 958 in Layer 3

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: 3.2838. Min Range: -3.2838

Max Act: 3.2838. Min Act: -0.1700

Data Index: 436886 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.2411. Min Act: -0.1700

Data Index: 2773794 (Open Web Text)

Max Activating Token Index: 833

Text #2

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.2061. Min Act: -0.1700

Data Index: 1548859 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1782. Min Act: -0.1700

Data Index: 2484694 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1667. Min Act: -0.1700

Data Index: 8397531 (Open Web Text)

Max Activating Token Index: 240

Text #5

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1640. Min Act: -0.1700

Data Index: 7742973 (Open Web Text)

Max Activating Token Index: 950

Text #6

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1294. Min Act: -0.1700

Data Index: 6985348 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1621. Min Act: -0.1700

Data Index: 1233899 (Open Web Text)

Max Activating Token Index: 467

Text #8

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1375. Min Act: -0.1700

Data Index: 1962371 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1287. Min Act: -0.1700

Data Index: 8439904 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1182. Min Act: -0.1700

Data Index: 192345 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1136. Min Act: -0.1700

Data Index: 3851416 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1322. Min Act: -0.1700

Data Index: 8425464 (Open Web Text)

Max Activating Token Index: 573

Text #13

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1176. Min Act: -0.1700

Data Index: 1969114 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.0746. Min Act: -0.1700

Data Index: 299263 (Open Web Text)

Max Activating Token Index: 1000

Text #15

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.0898. Min Act: -0.1700

Data Index: 6748203 (Open Web Text)

Max Activating Token Index: 409

Text #16

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.0913. Min Act: -0.1700

Data Index: 2022835 (Open Web Text)

Max Activating Token Index: 83

Text #17

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.1024. Min Act: -0.1700

Data Index: 3935007 (Open Web Text)

Max Activating Token Index: 186

Text #18

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.0791. Min Act: -0.1700

Data Index: 4848154 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 3.2838. Min Range: -3.2838

Max Act: 3.0693. Min Act: -0.1700

Data Index: 7624988 (Open Web Text)

Max Activating Token Index: 888