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

Dataset: Open Web Text

Neuron 2357 in Layer 2

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: 3.5401. Min Range: -3.5401

Max Act: 3.5401. Min Act: -0.1700

Data Index: 2198247 (Open Web Text)

Max Activating Token Index: 479

Text #1

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.5392. Min Act: -0.1700

Data Index: 4283835 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.5073. Min Act: -0.1700

Data Index: 3672392 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.5012. Min Act: -0.1700

Data Index: 4156855 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.5104. Min Act: -0.1700

Data Index: 6746383 (Open Web Text)

Max Activating Token Index: 457

Text #5

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4903. Min Act: -0.1700

Data Index: 3041813 (Open Web Text)

Max Activating Token Index: 135

Text #6

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4700. Min Act: -0.1700

Data Index: 3847093 (Open Web Text)

Max Activating Token Index: 501

Text #7

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4859. Min Act: -0.1700

Data Index: 8754542 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4317. Min Act: -0.1700

Data Index: 5779368 (Open Web Text)

Max Activating Token Index: 74

Text #9

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4381. Min Act: -0.1700

Data Index: 5612569 (Open Web Text)

Max Activating Token Index: 277

Text #10

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4087. Min Act: -0.1700

Data Index: 6971729 (Open Web Text)

Max Activating Token Index: 908

Text #11

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4508. Min Act: -0.1700

Data Index: 6746389 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4807. Min Act: -0.1700

Data Index: 1903744 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4287. Min Act: -0.1700

Data Index: 8578611 (Open Web Text)

Max Activating Token Index: 865

Text #14

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4137. Min Act: -0.1700

Data Index: 7622794 (Open Web Text)

Max Activating Token Index: 823

Text #15

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4014. Min Act: -0.1700

Data Index: 2038483 (Open Web Text)

Max Activating Token Index: 233

Text #16

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.3887. Min Act: -0.1700

Data Index: 6297499 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.4141. Min Act: -0.1700

Data Index: 949527 (Open Web Text)

Max Activating Token Index: 615

Text #18

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.3822. Min Act: -0.1700

Data Index: 6746380 (Open Web Text)

Max Activating Token Index: 944

Text #19

Max Range: 3.5401. Min Range: -3.5401

Max Act: 3.3998. Min Act: -0.1700

Data Index: 2793795 (Open Web Text)

Max Activating Token Index: 112