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

Dataset: Open Web Text

Neuron 4371 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2555. Min Range: -8.2555

Max Act: 8.2555. Min Act: -0.1700

Data Index: 8748538 (Open Web Text)

Max Activating Token Index: 856

Text #1

Max Range: 8.2555. Min Range: -8.2555

Max Act: 8.1930. Min Act: -0.1700

Data Index: 5898726 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 8.2555. Min Range: -8.2555

Max Act: 8.1305. Min Act: -0.1700

Data Index: 217131 (Open Web Text)

Max Activating Token Index: 874

Text #3

Max Range: 8.2555. Min Range: -8.2555

Max Act: 8.0680. Min Act: -0.1700

Data Index: 6747450 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.9430. Min Act: -0.1700

Data Index: 340203 (Open Web Text)

Max Activating Token Index: 958

Text #5

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.8805. Min Act: -0.1700

Data Index: 5250630 (Open Web Text)

Max Activating Token Index: 306

Text #6

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.8805. Min Act: -0.1700

Data Index: 6595425 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.8180. Min Act: -0.1700

Data Index: 5415096 (Open Web Text)

Max Activating Token Index: 301

Text #8

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.8180. Min Act: -0.1700

Data Index: 4112593 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.7555. Min Act: -0.1700

Data Index: 7905109 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.7555. Min Act: -0.1700

Data Index: 3278653 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.6930. Min Act: -0.1700

Data Index: 8432631 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.7555. Min Act: -0.1700

Data Index: 1429796 (Open Web Text)

Max Activating Token Index: 977

Text #13

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.6305. Min Act: -0.1700

Data Index: 2801948 (Open Web Text)

Max Activating Token Index: 843

Text #14

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.6305. Min Act: -0.1700

Data Index: 3102600 (Open Web Text)

Max Activating Token Index: 814

Text #15

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.6305. Min Act: -0.1700

Data Index: 7383816 (Open Web Text)

Max Activating Token Index: 951

Text #16

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.6305. Min Act: -0.1700

Data Index: 2582984 (Open Web Text)

Max Activating Token Index: 768

Text #17

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.5680. Min Act: -0.1700

Data Index: 485830 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.5680. Min Act: -0.1700

Data Index: 6217395 (Open Web Text)

Max Activating Token Index: 536

Text #19

Max Range: 8.2555. Min Range: -8.2555

Max Act: 7.5680. Min Act: -0.1700

Data Index: 3976742 (Open Web Text)

Max Activating Token Index: 105