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

Dataset: Open Web Text

Neuron 1937 in Layer 4

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: 3.1711. Min Range: -3.1711

Max Act: 3.1711. Min Act: -0.1700

Data Index: 3965619 (Open Web Text)

Max Activating Token Index: 942

Text #1

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1379. Min Act: -0.1700

Data Index: 4156994 (Open Web Text)

Max Activating Token Index: 416

Text #2

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1159. Min Act: -0.1700

Data Index: 4708829 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0818. Min Act: -0.1700

Data Index: 7847235 (Open Web Text)

Max Activating Token Index: 887

Text #4

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0874. Min Act: -0.1700

Data Index: 1374974 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1151. Min Act: -0.1700

Data Index: 2408269 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1119. Min Act: -0.1700

Data Index: 5880659 (Open Web Text)

Max Activating Token Index: 104

Text #7

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1439. Min Act: -0.1700

Data Index: 7915791 (Open Web Text)

Max Activating Token Index: 930

Text #8

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1180. Min Act: -0.1700

Data Index: 8149687 (Open Web Text)

Max Activating Token Index: 373

Text #9

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0877. Min Act: -0.1700

Data Index: 8008623 (Open Web Text)

Max Activating Token Index: 314

Text #10

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1447. Min Act: -0.1700

Data Index: 648485 (Open Web Text)

Max Activating Token Index: 700

Text #11

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0833. Min Act: -0.1700

Data Index: 1828734 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1057. Min Act: -0.1700

Data Index: 7948980 (Open Web Text)

Max Activating Token Index: 530

Text #13

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1123. Min Act: -0.1700

Data Index: 2764027 (Open Web Text)

Max Activating Token Index: 818

Text #14

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.1126. Min Act: -0.1700

Data Index: 10124 (Open Web Text)

Max Activating Token Index: 108

Text #15

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0761. Min Act: -0.1700

Data Index: 814330 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0828. Min Act: -0.1700

Data Index: 4536948 (Open Web Text)

Max Activating Token Index: 727

Text #17

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0832. Min Act: -0.1700

Data Index: 1897579 (Open Web Text)

Max Activating Token Index: 419

Text #18

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0954. Min Act: -0.1700

Data Index: 7358497 (Open Web Text)

Max Activating Token Index: 490

Text #19

Max Range: 3.1711. Min Range: -3.1711

Max Act: 3.0351. Min Act: -0.1700

Data Index: 2185609 (Open Web Text)

Max Activating Token Index: 671