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

Dataset: Open Web Text

Neuron 1226 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: 3.4133. Min Range: -3.4133

Max Act: 3.4133. Min Act: -0.1700

Data Index: 610493 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.2106. Min Act: -0.1700

Data Index: 8423604 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1967. Min Act: -0.1700

Data Index: 7114405 (Open Web Text)

Max Activating Token Index: 952

Text #3

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1946. Min Act: -0.1700

Data Index: 4591083 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1940. Min Act: -0.1700

Data Index: 361309 (Open Web Text)

Max Activating Token Index: 385

Text #5

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1870. Min Act: -0.1700

Data Index: 7426188 (Open Web Text)

Max Activating Token Index: 49

Text #6

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1854. Min Act: -0.1700

Data Index: 2828266 (Open Web Text)

Max Activating Token Index: 657

Text #7

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1853. Min Act: -0.1700

Data Index: 4244060 (Open Web Text)

Max Activating Token Index: 251

Text #8

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1770. Min Act: -0.1700

Data Index: 2525683 (Open Web Text)

Max Activating Token Index: 654

Text #9

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1793. Min Act: -0.1700

Data Index: 1041654 (Open Web Text)

Max Activating Token Index: 34

Text #10

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1703. Min Act: -0.1700

Data Index: 4160355 (Open Web Text)

Max Activating Token Index: 699

Text #11

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1623. Min Act: -0.1700

Data Index: 4714375 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1586. Min Act: -0.1700

Data Index: 4907312 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1516. Min Act: -0.1700

Data Index: 8211587 (Open Web Text)

Max Activating Token Index: 901

Text #14

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1441. Min Act: -0.1700

Data Index: 8620237 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1430. Min Act: -0.1700

Data Index: 867962 (Open Web Text)

Max Activating Token Index: 659

Text #16

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1350. Min Act: -0.1700

Data Index: 8223290 (Open Web Text)

Max Activating Token Index: 903

Text #17

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1220. Min Act: -0.1700

Data Index: 5770611 (Open Web Text)

Max Activating Token Index: 73

Text #18

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1307. Min Act: -0.1700

Data Index: 6233503 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 3.4133. Min Range: -3.4133

Max Act: 3.1242. Min Act: -0.1700

Data Index: 8047202 (Open Web Text)

Max Activating Token Index: 4