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

Dataset: Open Web Text

Neuron 665 in Layer 2

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: 3.0377. Min Range: -3.0377

Max Act: 3.0377. Min Act: -0.1700

Data Index: 5214712 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.0377. Min Range: -3.0377

Max Act: 3.0227. Min Act: -0.1700

Data Index: 8362152 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.9616. Min Act: -0.1700

Data Index: 4088077 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.9511. Min Act: -0.1700

Data Index: 7824239 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.9491. Min Act: -0.1700

Data Index: 6715964 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.9163. Min Act: -0.1700

Data Index: 3391270 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8838. Min Act: -0.1700

Data Index: 4402447 (Open Web Text)

Max Activating Token Index: 50

Text #7

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8738. Min Act: -0.1700

Data Index: 5742924 (Open Web Text)

Max Activating Token Index: 22

Text #8

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8552. Min Act: -0.1700

Data Index: 8517323 (Open Web Text)

Max Activating Token Index: 36

Text #9

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8350. Min Act: -0.1700

Data Index: 4901676 (Open Web Text)

Max Activating Token Index: 29

Text #10

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8417. Min Act: -0.1700

Data Index: 2362051 (Open Web Text)

Max Activating Token Index: 300

Text #11

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8279. Min Act: -0.1700

Data Index: 1632374 (Open Web Text)

Max Activating Token Index: 458

Text #12

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8061. Min Act: -0.1700

Data Index: 2362041 (Open Web Text)

Max Activating Token Index: 705

Text #13

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7848. Min Act: -0.1700

Data Index: 3359005 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7899. Min Act: -0.1700

Data Index: 3406422 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8045. Min Act: -0.1700

Data Index: 3479660 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8032. Min Act: -0.1700

Data Index: 2502005 (Open Web Text)

Max Activating Token Index: 822

Text #17

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7789. Min Act: -0.1700

Data Index: 2362044 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7746. Min Act: -0.1700

Data Index: 6154365 (Open Web Text)

Max Activating Token Index: 915

Text #19

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7865. Min Act: -0.1700

Data Index: 263207 (Open Web Text)

Max Activating Token Index: 733