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

Dataset: Open Web Text

Neuron 1087 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: 3.2654. Min Range: -3.2654

Max Act: 3.2654. Min Act: -0.1700

Data Index: 158706 (Open Web Text)

Max Activating Token Index: 697

Text #1

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.2264. Min Act: -0.1700

Data Index: 2870782 (Open Web Text)

Max Activating Token Index: 356

Text #2

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1590. Min Act: -0.1700

Data Index: 8174992 (Open Web Text)

Max Activating Token Index: 528

Text #3

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1390. Min Act: -0.1700

Data Index: 7041797 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1344. Min Act: -0.1700

Data Index: 1820899 (Open Web Text)

Max Activating Token Index: 76

Text #5

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1369. Min Act: -0.1700

Data Index: 4623508 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1188. Min Act: -0.1700

Data Index: 2768277 (Open Web Text)

Max Activating Token Index: 312

Text #7

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1200. Min Act: -0.1700

Data Index: 8012328 (Open Web Text)

Max Activating Token Index: 82

Text #8

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1248. Min Act: -0.1700

Data Index: 2359713 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.1272. Min Act: -0.1700

Data Index: 1324193 (Open Web Text)

Max Activating Token Index: 427

Text #10

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0995. Min Act: -0.1700

Data Index: 7588465 (Open Web Text)

Max Activating Token Index: 692

Text #11

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0823. Min Act: -0.1700

Data Index: 4256787 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0842. Min Act: -0.1700

Data Index: 610103 (Open Web Text)

Max Activating Token Index: 109

Text #13

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0759. Min Act: -0.1700

Data Index: 1927326 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0447. Min Act: -0.1700

Data Index: 4906619 (Open Web Text)

Max Activating Token Index: 88

Text #15

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0508. Min Act: -0.1700

Data Index: 3336519 (Open Web Text)

Max Activating Token Index: 49

Text #16

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0377. Min Act: -0.1700

Data Index: 1401449 (Open Web Text)

Max Activating Token Index: 65

Text #17

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0304. Min Act: -0.1700

Data Index: 2125449 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0281. Min Act: -0.1700

Data Index: 2308254 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 3.2654. Min Range: -3.2654

Max Act: 3.0442. Min Act: -0.1700

Data Index: 1256525 (Open Web Text)

Max Activating Token Index: 142