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

Dataset: Open Web Text

Neuron 2371 in Layer 3

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: 3.2130. Min Range: -3.2130

Max Act: 3.2130. Min Act: -0.1700

Data Index: 7994912 (Open Web Text)

Max Activating Token Index: 846

Text #1

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1879. Min Act: -0.1700

Data Index: 5446617 (Open Web Text)

Max Activating Token Index: 77

Text #2

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1892. Min Act: -0.1700

Data Index: 3725701 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1830. Min Act: -0.1700

Data Index: 7265075 (Open Web Text)

Max Activating Token Index: 139

Text #4

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1720. Min Act: -0.1700

Data Index: 6593221 (Open Web Text)

Max Activating Token Index: 513

Text #5

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1453. Min Act: -0.1700

Data Index: 6635985 (Open Web Text)

Max Activating Token Index: 627

Text #6

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1426. Min Act: -0.1700

Data Index: 8304908 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1420. Min Act: -0.1700

Data Index: 1680739 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1192. Min Act: -0.1700

Data Index: 5766788 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1221. Min Act: -0.1700

Data Index: 2695027 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1359. Min Act: -0.1700

Data Index: 5360984 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1249. Min Act: -0.1700

Data Index: 4265396 (Open Web Text)

Max Activating Token Index: 162

Text #12

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1114. Min Act: -0.1700

Data Index: 7368336 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.0772. Min Act: -0.1700

Data Index: 499440 (Open Web Text)

Max Activating Token Index: 1012

Text #14

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1027. Min Act: -0.1700

Data Index: 7128183 (Open Web Text)

Max Activating Token Index: 31

Text #15

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1141. Min Act: -0.1700

Data Index: 1908175 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1186. Min Act: -0.1700

Data Index: 4333179 (Open Web Text)

Max Activating Token Index: 53

Text #17

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1189. Min Act: -0.1700

Data Index: 6474767 (Open Web Text)

Max Activating Token Index: 64

Text #18

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1232. Min Act: -0.1700

Data Index: 7635168 (Open Web Text)

Max Activating Token Index: 481

Text #19

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1010. Min Act: -0.1700

Data Index: 6202176 (Open Web Text)

Max Activating Token Index: 172