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

Dataset: Open Web Text

Neuron 1964 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: 1.5675. Min Range: -1.5675

Max Act: 1.5675. Min Act: -0.1699

Data Index: 7866415 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5539. Min Act: -0.1700

Data Index: 8348281 (Open Web Text)

Max Activating Token Index: 930

Text #2

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5317. Min Act: -0.1700

Data Index: 3065267 (Open Web Text)

Max Activating Token Index: 101

Text #3

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5286. Min Act: -0.1696

Data Index: 282471 (Open Web Text)

Max Activating Token Index: 556

Text #4

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5341. Min Act: -0.1698

Data Index: 8379405 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5251. Min Act: -0.1700

Data Index: 5723417 (Open Web Text)

Max Activating Token Index: 539

Text #6

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5130. Min Act: -0.1700

Data Index: 8039780 (Open Web Text)

Max Activating Token Index: 894

Text #7

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5286. Min Act: -0.1700

Data Index: 1025079 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5238. Min Act: -0.1700

Data Index: 6645216 (Open Web Text)

Max Activating Token Index: 751

Text #9

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5139. Min Act: -0.1700

Data Index: 29388 (Open Web Text)

Max Activating Token Index: 535

Text #10

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5233. Min Act: -0.1700

Data Index: 8646585 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5141. Min Act: -0.1698

Data Index: 5059826 (Open Web Text)

Max Activating Token Index: 383

Text #12

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5021. Min Act: -0.1700

Data Index: 1318345 (Open Web Text)

Max Activating Token Index: 534

Text #13

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5050. Min Act: -0.1700

Data Index: 5043399 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5021. Min Act: -0.1700

Data Index: 124901 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5010. Min Act: -0.1694

Data Index: 7438468 (Open Web Text)

Max Activating Token Index: 828

Text #16

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4992. Min Act: -0.1699

Data Index: 7124862 (Open Web Text)

Max Activating Token Index: 784

Text #17

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4977. Min Act: -0.1496

Data Index: 7529224 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.5005. Min Act: -0.1699

Data Index: 8357802 (Open Web Text)

Max Activating Token Index: 454

Text #19

Max Range: 1.5675. Min Range: -1.5675

Max Act: 1.4932. Min Act: -0.1700

Data Index: 1308416 (Open Web Text)

Max Activating Token Index: 830