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

Dataset: Open Web Text

Neuron 1450 in Layer 6

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: 5.2763. Min Range: -5.2763

Max Act: 5.2763. Min Act: -0.1700

Data Index: 4548404 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.2552. Min Act: -0.1700

Data Index: 5470948 (Open Web Text)

Max Activating Token Index: 725

Text #2

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.2050. Min Act: -0.1700

Data Index: 4843613 (Open Web Text)

Max Activating Token Index: 434

Text #3

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.2196. Min Act: -0.1700

Data Index: 5375378 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.2165. Min Act: -0.1700

Data Index: 3910249 (Open Web Text)

Max Activating Token Index: 567

Text #5

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.2028. Min Act: -0.1700

Data Index: 3186682 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.1675. Min Act: -0.1700

Data Index: 7250311 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.1410. Min Act: -0.1700

Data Index: 6515829 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.1745. Min Act: -0.1700

Data Index: 3184919 (Open Web Text)

Max Activating Token Index: 650

Text #9

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.1163. Min Act: -0.1700

Data Index: 1365247 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.1006. Min Act: -0.1700

Data Index: 4160118 (Open Web Text)

Max Activating Token Index: 298

Text #11

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.1279. Min Act: -0.1700

Data Index: 1818306 (Open Web Text)

Max Activating Token Index: 937

Text #12

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.1114. Min Act: -0.1700

Data Index: 4564512 (Open Web Text)

Max Activating Token Index: 933

Text #13

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.1143. Min Act: -0.1700

Data Index: 8527084 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.0852. Min Act: -0.1700

Data Index: 5104274 (Open Web Text)

Max Activating Token Index: 311

Text #15

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.0492. Min Act: -0.1700

Data Index: 1930903 (Open Web Text)

Max Activating Token Index: 826

Text #16

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.0553. Min Act: -0.1700

Data Index: 5839090 (Open Web Text)

Max Activating Token Index: 861

Text #17

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.0836. Min Act: -0.1700

Data Index: 4858334 (Open Web Text)

Max Activating Token Index: 895

Text #18

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.0591. Min Act: -0.1700

Data Index: 876773 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 5.2763. Min Range: -5.2763

Max Act: 5.0625. Min Act: -0.1700

Data Index: 2403408 (Open Web Text)

Max Activating Token Index: 688