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

Dataset: Open Web Text

Neuron 1424 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: 4.8826. Min Range: -4.8826

Max Act: 4.8826. Min Act: -0.1700

Data Index: 5324144 (Open Web Text)

Max Activating Token Index: 506

Text #1

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.2850. Min Act: -0.1700

Data Index: 7791833 (Open Web Text)

Max Activating Token Index: 347

Text #2

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.3237. Min Act: -0.1700

Data Index: 8746452 (Open Web Text)

Max Activating Token Index: 429

Text #3

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.2689. Min Act: -0.1700

Data Index: 689144 (Open Web Text)

Max Activating Token Index: 763

Text #4

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.2771. Min Act: -0.1700

Data Index: 461661 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1873. Min Act: -0.1700

Data Index: 6400893 (Open Web Text)

Max Activating Token Index: 853

Text #6

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1817. Min Act: -0.1700

Data Index: 2683384 (Open Web Text)

Max Activating Token Index: 748

Text #7

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1952. Min Act: -0.1700

Data Index: 6530881 (Open Web Text)

Max Activating Token Index: 773

Text #8

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1989. Min Act: -0.1700

Data Index: 5836051 (Open Web Text)

Max Activating Token Index: 216

Text #9

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1711. Min Act: -0.1700

Data Index: 8376916 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1703. Min Act: -0.1700

Data Index: 2503008 (Open Web Text)

Max Activating Token Index: 866

Text #11

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1504. Min Act: -0.1700

Data Index: 5531020 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1421. Min Act: -0.1700

Data Index: 1915472 (Open Web Text)

Max Activating Token Index: 710

Text #13

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1643. Min Act: -0.1700

Data Index: 7865485 (Open Web Text)

Max Activating Token Index: 974

Text #14

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1214. Min Act: -0.1700

Data Index: 3558068 (Open Web Text)

Max Activating Token Index: 842

Text #15

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1661. Min Act: -0.1700

Data Index: 7982363 (Open Web Text)

Max Activating Token Index: 143

Text #16

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1187. Min Act: -0.1700

Data Index: 6617143 (Open Web Text)

Max Activating Token Index: 136

Text #17

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1090. Min Act: -0.1700

Data Index: 2938840 (Open Web Text)

Max Activating Token Index: 598

Text #18

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1260. Min Act: -0.1700

Data Index: 6989894 (Open Web Text)

Max Activating Token Index: 199

Text #19

Max Range: 4.8826. Min Range: -4.8826

Max Act: 4.1007. Min Act: -0.1700

Data Index: 5075796 (Open Web Text)

Max Activating Token Index: 446