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

Dataset: Open Web Text

Neuron 1092 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: 5.8011. Min Range: -5.8011

Max Act: 5.7322. Min Act: -0.1700

Data Index: 3620900 (Open Web Text)

Max Activating Token Index: 757

Text #1

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.7615. Min Act: -0.1700

Data Index: 680104 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.8011. Min Act: -0.1700

Data Index: 1570665 (Open Web Text)

Max Activating Token Index: 660

Text #3

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.5478. Min Act: -0.1700

Data Index: 7209083 (Open Web Text)

Max Activating Token Index: 756

Text #4

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.5677. Min Act: -0.1700

Data Index: 1615275 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.5106. Min Act: -0.1700

Data Index: 8084082 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.4835. Min Act: -0.1700

Data Index: 4103153 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.4787. Min Act: -0.1700

Data Index: 4203500 (Open Web Text)

Max Activating Token Index: 845

Text #8

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.5086. Min Act: -0.1700

Data Index: 6678917 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.4931. Min Act: -0.1700

Data Index: 1996727 (Open Web Text)

Max Activating Token Index: 597

Text #10

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.4413. Min Act: -0.1700

Data Index: 15536 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.4395. Min Act: -0.1700

Data Index: 8441974 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.4067. Min Act: -0.1700

Data Index: 4326902 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.3673. Min Act: -0.1700

Data Index: 1909095 (Open Web Text)

Max Activating Token Index: 143

Text #14

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.3858. Min Act: -0.1700

Data Index: 2442582 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.3784. Min Act: -0.1700

Data Index: 378324 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.3677. Min Act: -0.1700

Data Index: 7703706 (Open Web Text)

Max Activating Token Index: 126

Text #17

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.3848. Min Act: -0.1700

Data Index: 1456499 (Open Web Text)

Max Activating Token Index: 547

Text #18

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.3648. Min Act: -0.1700

Data Index: 663681 (Open Web Text)

Max Activating Token Index: 542

Text #19

Max Range: 5.8011. Min Range: -5.8011

Max Act: 5.3780. Min Act: -0.1700

Data Index: 1633957 (Open Web Text)

Max Activating Token Index: 530