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

Dataset: Open Web Text

Neuron 1476 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: 4.7492. Min Range: -4.7492

Max Act: 4.7492. Min Act: -0.1700

Data Index: 7967498 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.7274. Min Act: -0.1700

Data Index: 6270150 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.7298. Min Act: -0.1700

Data Index: 5366498 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6978. Min Act: -0.1700

Data Index: 1892561 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.7141. Min Act: -0.1700

Data Index: 7143234 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6981. Min Act: -0.1700

Data Index: 1377860 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6981. Min Act: -0.1700

Data Index: 3192208 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6732. Min Act: -0.1700

Data Index: 1877772 (Open Web Text)

Max Activating Token Index: 43

Text #8

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6820. Min Act: -0.1700

Data Index: 6545861 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6589. Min Act: -0.1700

Data Index: 5758123 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6810. Min Act: -0.1700

Data Index: 5260804 (Open Web Text)

Max Activating Token Index: 30

Text #11

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6643. Min Act: -0.1700

Data Index: 8147066 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6807. Min Act: -0.1700

Data Index: 754061 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6877. Min Act: -0.1700

Data Index: 919911 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6702. Min Act: -0.1700

Data Index: 3365704 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6468. Min Act: -0.1700

Data Index: 2148094 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6395. Min Act: -0.1700

Data Index: 2524419 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6299. Min Act: -0.1700

Data Index: 4110825 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6608. Min Act: -0.1700

Data Index: 356710 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.7492. Min Range: -4.7492

Max Act: 4.6655. Min Act: -0.1700

Data Index: 5409784 (Open Web Text)

Max Activating Token Index: 10