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

Dataset: Open Web Text

Neuron 1881 in Layer 5

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: 4.8219. Min Range: -4.8219

Max Act: 4.8219. Min Act: -0.1700

Data Index: 8422116 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.8149. Min Act: -0.1700

Data Index: 6985153 (Open Web Text)

Max Activating Token Index: 564

Text #2

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7961. Min Act: -0.1700

Data Index: 2908987 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7768. Min Act: -0.1700

Data Index: 4703105 (Open Web Text)

Max Activating Token Index: 312

Text #4

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7973. Min Act: -0.1700

Data Index: 1242529 (Open Web Text)

Max Activating Token Index: 60

Text #5

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7959. Min Act: -0.1700

Data Index: 1907965 (Open Web Text)

Max Activating Token Index: 714

Text #6

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7850. Min Act: -0.1700

Data Index: 258250 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7782. Min Act: -0.1700

Data Index: 4209450 (Open Web Text)

Max Activating Token Index: 373

Text #8

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7276. Min Act: -0.1700

Data Index: 1431303 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7286. Min Act: -0.1700

Data Index: 6351602 (Open Web Text)

Max Activating Token Index: 433

Text #10

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7375. Min Act: -0.1700

Data Index: 4167942 (Open Web Text)

Max Activating Token Index: 662

Text #11

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7480. Min Act: -0.1700

Data Index: 2021403 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.6946. Min Act: -0.1700

Data Index: 6216019 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.6906. Min Act: -0.1700

Data Index: 6338768 (Open Web Text)

Max Activating Token Index: 595

Text #14

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.6985. Min Act: -0.1700

Data Index: 5875831 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.6975. Min Act: -0.1700

Data Index: 8626469 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7165. Min Act: -0.1700

Data Index: 5425667 (Open Web Text)

Max Activating Token Index: 861

Text #17

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.7196. Min Act: -0.1700

Data Index: 2156218 (Open Web Text)

Max Activating Token Index: 667

Text #18

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.6636. Min Act: -0.1700

Data Index: 5840941 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 4.8219. Min Range: -4.8219

Max Act: 4.6611. Min Act: -0.1700

Data Index: 3563274 (Open Web Text)

Max Activating Token Index: 519