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

Dataset: Open Web Text

Neuron 1939 in Layer 2

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: 6.1813. Min Range: -6.1813

Max Act: 6.1813. Min Act: -0.1700

Data Index: 3967117 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.1271. Min Act: -0.1700

Data Index: 5661360 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.1271. Min Act: -0.1700

Data Index: 7299084 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.1271. Min Act: -0.1700

Data Index: 6839361 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0778. Min Act: -0.1700

Data Index: 6739215 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0738. Min Act: -0.1700

Data Index: 2845619 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0794. Min Act: -0.1700

Data Index: 7474772 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0615. Min Act: -0.1700

Data Index: 7404204 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0651. Min Act: -0.1700

Data Index: 1114371 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0458. Min Act: -0.1700

Data Index: 1695417 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0454. Min Act: -0.1700

Data Index: 391559 (Open Web Text)

Max Activating Token Index: 860

Text #11

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0798. Min Act: -0.1700

Data Index: 6383375 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0592. Min Act: -0.1700

Data Index: 1938072 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0538. Min Act: -0.1700

Data Index: 5664647 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0234. Min Act: -0.1700

Data Index: 3240680 (Open Web Text)

Max Activating Token Index: 746

Text #15

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0170. Min Act: -0.1700

Data Index: 1652567 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0396. Min Act: -0.1700

Data Index: 5222188 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0282. Min Act: -0.1700

Data Index: 368878 (Open Web Text)

Max Activating Token Index: 215

Text #18

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0026. Min Act: -0.1700

Data Index: 1505526 (Open Web Text)

Max Activating Token Index: 140

Text #19

Max Range: 6.1813. Min Range: -6.1813

Max Act: 6.0178. Min Act: -0.1700

Data Index: 7879536 (Open Web Text)

Max Activating Token Index: 6