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

Dataset: Open Web Text

Neuron 2802 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: 4.2911. Min Range: -4.2911

Max Act: 4.2911. Min Act: -0.1700

Data Index: 6062275 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.2089. Min Act: -0.1700

Data Index: 5501504 (Open Web Text)

Max Activating Token Index: 681

Text #2

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1951. Min Act: -0.1700

Data Index: 7557502 (Open Web Text)

Max Activating Token Index: 127

Text #3

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1879. Min Act: -0.1700

Data Index: 5828359 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1797. Min Act: -0.1700

Data Index: 4146218 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1773. Min Act: -0.1700

Data Index: 8827878 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1746. Min Act: -0.1700

Data Index: 4526608 (Open Web Text)

Max Activating Token Index: 183

Text #7

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1512. Min Act: -0.1700

Data Index: 7495687 (Open Web Text)

Max Activating Token Index: 233

Text #8

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1761. Min Act: -0.1700

Data Index: 2185188 (Open Web Text)

Max Activating Token Index: 958

Text #9

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1792. Min Act: -0.1700

Data Index: 5007775 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1770. Min Act: -0.1700

Data Index: 3875235 (Open Web Text)

Max Activating Token Index: 571

Text #11

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1649. Min Act: -0.1700

Data Index: 7199895 (Open Web Text)

Max Activating Token Index: 466

Text #12

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1728. Min Act: -0.1700

Data Index: 6142864 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1351. Min Act: -0.1700

Data Index: 2124030 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1326. Min Act: -0.1700

Data Index: 4502370 (Open Web Text)

Max Activating Token Index: 335

Text #15

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1402. Min Act: -0.1700

Data Index: 8664817 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1377. Min Act: -0.1700

Data Index: 7638333 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1321. Min Act: -0.1700

Data Index: 81332 (Open Web Text)

Max Activating Token Index: 98

Text #18

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.0836. Min Act: -0.1700

Data Index: 7051515 (Open Web Text)

Max Activating Token Index: 717

Text #19

Max Range: 4.2911. Min Range: -4.2911

Max Act: 4.1142. Min Act: -0.1700

Data Index: 1873248 (Open Web Text)

Max Activating Token Index: 855