Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 1080 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.2555. Min Act: -0.1619

Data Index: 4980581 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.2555. Min Act: -0.1631

Data Index: 221832 (Open Web Text)

Max Activating Token Index: 870

Text #2

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.2202. Min Act: -0.1698

Data Index: 2096500 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1850. Min Act: -0.1660

Data Index: 4762493 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1850. Min Act: -0.1700

Data Index: 2204480 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1498. Min Act: -0.1696

Data Index: 680950 (Open Web Text)

Max Activating Token Index: 26

Text #6

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1674. Min Act: -0.1700

Data Index: 2674272 (Open Web Text)

Max Activating Token Index: 674

Text #7

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1322. Min Act: -0.1609

Data Index: 6646385 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1322. Min Act: -0.1525

Data Index: 8313050 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1322. Min Act: -0.1694

Data Index: 402569 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1147. Min Act: -0.1698

Data Index: 5489398 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0972. Min Act: -0.1697

Data Index: 7740682 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0972. Min Act: -0.1465

Data Index: 7100901 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1147. Min Act: -0.1660

Data Index: 5472067 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0972. Min Act: -0.1225

Data Index: 6748169 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0972. Min Act: -0.1677

Data Index: 8016740 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0972. Min Act: -0.1425

Data Index: 2099097 (Open Web Text)

Max Activating Token Index: 32

Text #17

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0797. Min Act: -0.1244

Data Index: 5522327 (Open Web Text)

Max Activating Token Index: 800

Text #18

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0797. Min Act: -0.1700

Data Index: 8220281 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0622. Min Act: -0.1700

Data Index: 7373548 (Open Web Text)

Max Activating Token Index: 23