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

Dataset: Open Web Text

Neuron 1914 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: 4.2650. Min Range: -4.2650

Max Act: 4.2650. Min Act: -0.1700

Data Index: 4916647 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.2077. Min Act: -0.1700

Data Index: 6916648 (Open Web Text)

Max Activating Token Index: 855

Text #2

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.1793. Min Act: -0.1700

Data Index: 691047 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.1626. Min Act: -0.1700

Data Index: 5150606 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.1150. Min Act: -0.1700

Data Index: 1100601 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.1258. Min Act: -0.1700

Data Index: 1993746 (Open Web Text)

Max Activating Token Index: 122

Text #6

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.1348. Min Act: -0.1700

Data Index: 5824860 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0846. Min Act: -0.1700

Data Index: 1414774 (Open Web Text)

Max Activating Token Index: 675

Text #8

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0877. Min Act: -0.1700

Data Index: 2043602 (Open Web Text)

Max Activating Token Index: 216

Text #9

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0806. Min Act: -0.1700

Data Index: 5775206 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0810. Min Act: -0.1700

Data Index: 1832024 (Open Web Text)

Max Activating Token Index: 444

Text #11

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0437. Min Act: -0.1700

Data Index: 4802813 (Open Web Text)

Max Activating Token Index: 279

Text #12

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0705. Min Act: -0.1700

Data Index: 2930951 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0654. Min Act: -0.1700

Data Index: 917525 (Open Web Text)

Max Activating Token Index: 218

Text #14

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0789. Min Act: -0.1700

Data Index: 4529441 (Open Web Text)

Max Activating Token Index: 653

Text #15

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0579. Min Act: -0.1700

Data Index: 4294245 (Open Web Text)

Max Activating Token Index: 296

Text #16

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0798. Min Act: -0.1700

Data Index: 127932 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0446. Min Act: -0.1700

Data Index: 4219953 (Open Web Text)

Max Activating Token Index: 146

Text #18

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0636. Min Act: -0.1700

Data Index: 1528418 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 4.2650. Min Range: -4.2650

Max Act: 4.0670. Min Act: -0.1700

Data Index: 4136808 (Open Web Text)

Max Activating Token Index: 349