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

Dataset: Open Web Text

Neuron 1659 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: 3.3000. Min Range: -3.3000

Max Act: 3.3000. Min Act: -0.1700

Data Index: 2106038 (Open Web Text)

Max Activating Token Index: 905

Text #1

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1225. Min Act: -0.1700

Data Index: 1773951 (Open Web Text)

Max Activating Token Index: 165

Text #2

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.0130. Min Act: -0.1700

Data Index: 1602526 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9736. Min Act: -0.1700

Data Index: 5961857 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9729. Min Act: -0.1700

Data Index: 5760655 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9507. Min Act: -0.1700

Data Index: 5107885 (Open Web Text)

Max Activating Token Index: 577

Text #6

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9374. Min Act: -0.1700

Data Index: 3720757 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9407. Min Act: -0.1700

Data Index: 3314705 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9244. Min Act: -0.1700

Data Index: 225637 (Open Web Text)

Max Activating Token Index: 396

Text #9

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9262. Min Act: -0.1700

Data Index: 5823613 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9196. Min Act: -0.1700

Data Index: 749286 (Open Web Text)

Max Activating Token Index: 598

Text #11

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9053. Min Act: -0.1700

Data Index: 8331801 (Open Web Text)

Max Activating Token Index: 902

Text #12

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9366. Min Act: -0.1700

Data Index: 5961858 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9112. Min Act: -0.1700

Data Index: 797121 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9130. Min Act: -0.1700

Data Index: 3689298 (Open Web Text)

Max Activating Token Index: 583

Text #15

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9180. Min Act: -0.1700

Data Index: 3824653 (Open Web Text)

Max Activating Token Index: 60

Text #16

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9068. Min Act: -0.1700

Data Index: 2056905 (Open Web Text)

Max Activating Token Index: 305

Text #17

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.9228. Min Act: -0.1700

Data Index: 6725849 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.8989. Min Act: -0.1700

Data Index: 5442402 (Open Web Text)

Max Activating Token Index: 68

Text #19

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.8845. Min Act: -0.1700

Data Index: 5819254 (Open Web Text)

Max Activating Token Index: 498