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

Dataset: Open Web Text

Neuron 2468 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: 1.6029. Min Range: -1.6029

Max Act: 1.6029. Min Act: -0.1372

Data Index: 5996462 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5768. Min Act: -0.1700

Data Index: 3900741 (Open Web Text)

Max Activating Token Index: 662

Text #2

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5651. Min Act: -0.1700

Data Index: 3323024 (Open Web Text)

Max Activating Token Index: 468

Text #3

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5610. Min Act: -0.1690

Data Index: 6064524 (Open Web Text)

Max Activating Token Index: 210

Text #4

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5558. Min Act: -0.1700

Data Index: 4034641 (Open Web Text)

Max Activating Token Index: 252

Text #5

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5529. Min Act: -0.1700

Data Index: 5194112 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5419. Min Act: -0.1699

Data Index: 7871721 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5420. Min Act: -0.1700

Data Index: 4117600 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5546. Min Act: -0.1700

Data Index: 2808916 (Open Web Text)

Max Activating Token Index: 674

Text #9

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5510. Min Act: -0.1698

Data Index: 8764188 (Open Web Text)

Max Activating Token Index: 242

Text #10

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5539. Min Act: -0.1700

Data Index: 1431498 (Open Web Text)

Max Activating Token Index: 571

Text #11

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5388. Min Act: -0.1700

Data Index: 3095270 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5313. Min Act: -0.1700

Data Index: 4655826 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5365. Min Act: -0.1700

Data Index: 5593678 (Open Web Text)

Max Activating Token Index: 989

Text #14

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5315. Min Act: -0.1700

Data Index: 1263589 (Open Web Text)

Max Activating Token Index: 1003

Text #15

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5265. Min Act: -0.1700

Data Index: 4795493 (Open Web Text)

Max Activating Token Index: 60

Text #16

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5326. Min Act: -0.1700

Data Index: 8235518 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5225. Min Act: -0.1700

Data Index: 5210351 (Open Web Text)

Max Activating Token Index: 828

Text #18

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5196. Min Act: -0.1699

Data Index: 8702372 (Open Web Text)

Max Activating Token Index: 145

Text #19

Max Range: 1.6029. Min Range: -1.6029

Max Act: 1.5184. Min Act: -0.1700

Data Index: 1477113 (Open Web Text)

Max Activating Token Index: 804