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

Dataset: Open Web Text

Neuron 2477 in Layer 1

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: 1.5334. Min Range: -1.5334

Max Act: 1.5334. Min Act: -0.1696

Data Index: 6283457 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5334. Min Act: -0.1700

Data Index: 3521964 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5334. Min Act: -0.1700

Data Index: 1673667 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5176. Min Act: -0.1700

Data Index: 1984846 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5176. Min Act: -0.1691

Data Index: 4716792 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5104. Min Act: -0.1698

Data Index: 6017223 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5104. Min Act: -0.1697

Data Index: 1236172 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5176. Min Act: -0.1700

Data Index: 8597855 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5053. Min Act: -0.1700

Data Index: 76906 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5063. Min Act: -0.1676

Data Index: 6653869 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4992. Min Act: -0.1700

Data Index: 3172423 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5053. Min Act: -0.1700

Data Index: 5693278 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4878. Min Act: -0.1697

Data Index: 1433317 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4685. Min Act: -0.1524

Data Index: 6048716 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4728. Min Act: -0.1691

Data Index: 4113787 (Open Web Text)

Max Activating Token Index: 258

Text #15

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4607. Min Act: -0.1700

Data Index: 8015625 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4504. Min Act: -0.1699

Data Index: 2171903 (Open Web Text)

Max Activating Token Index: 688

Text #17

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4607. Min Act: -0.1699

Data Index: 799966 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4607. Min Act: -0.1700

Data Index: 6347134 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4610. Min Act: -0.1700

Data Index: 4620201 (Open Web Text)

Max Activating Token Index: 591