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

Dataset: Open Web Text

Neuron 447 in Layer 0

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: 3.2242. Min Range: -3.2242

Max Act: 3.2242. Min Act: -0.1700

Data Index: 4391010 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.2178. Min Act: -0.1700

Data Index: 7789198 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1740. Min Act: -0.1700

Data Index: 5011616 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1838. Min Act: -0.1700

Data Index: 6477965 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1790. Min Act: -0.1700

Data Index: 4098770 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1901. Min Act: -0.1700

Data Index: 7411413 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1836. Min Act: -0.1700

Data Index: 1676608 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1468. Min Act: -0.1700

Data Index: 8241618 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1559. Min Act: -0.1700

Data Index: 4687602 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1558. Min Act: -0.1700

Data Index: 8399682 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1528. Min Act: -0.1700

Data Index: 1528393 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1377. Min Act: -0.1700

Data Index: 782310 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1368. Min Act: -0.1700

Data Index: 905003 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1425. Min Act: -0.1700

Data Index: 2066021 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1300. Min Act: -0.1700

Data Index: 7873907 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1343. Min Act: -0.1700

Data Index: 6887461 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1360. Min Act: -0.1700

Data Index: 2437693 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1440. Min Act: -0.1700

Data Index: 2128438 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1428. Min Act: -0.1700

Data Index: 8765965 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1232. Min Act: -0.1700

Data Index: 2389365 (Open Web Text)

Max Activating Token Index: 4