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

Dataset: Open Web Text

Neuron 930 in Layer 6

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: 4.9147. Min Range: -4.9147

Max Act: 4.9147. Min Act: -0.1700

Data Index: 3666232 (Open Web Text)

Max Activating Token Index: 293

Text #1

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.8148. Min Act: -0.1700

Data Index: 3449534 (Open Web Text)

Max Activating Token Index: 676

Text #2

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7582. Min Act: -0.1700

Data Index: 705587 (Open Web Text)

Max Activating Token Index: 369

Text #3

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7460. Min Act: -0.1700

Data Index: 1785444 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7343. Min Act: -0.1700

Data Index: 901043 (Open Web Text)

Max Activating Token Index: 1006

Text #5

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7165. Min Act: -0.1700

Data Index: 1932687 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7235. Min Act: -0.1700

Data Index: 2911125 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7339. Min Act: -0.1700

Data Index: 7117903 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7316. Min Act: -0.1700

Data Index: 1948287 (Open Web Text)

Max Activating Token Index: 299

Text #9

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.6948. Min Act: -0.1700

Data Index: 2462480 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.6961. Min Act: -0.1700

Data Index: 1441615 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7114. Min Act: -0.1700

Data Index: 290902 (Open Web Text)

Max Activating Token Index: 480

Text #12

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7037. Min Act: -0.1700

Data Index: 5522535 (Open Web Text)

Max Activating Token Index: 367

Text #13

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7137. Min Act: -0.1700

Data Index: 781940 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7102. Min Act: -0.1700

Data Index: 2938302 (Open Web Text)

Max Activating Token Index: 920

Text #15

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.7172. Min Act: -0.1700

Data Index: 3974916 (Open Web Text)

Max Activating Token Index: 38

Text #16

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.6865. Min Act: -0.1700

Data Index: 998273 (Open Web Text)

Max Activating Token Index: 377

Text #17

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.6998. Min Act: -0.1700

Data Index: 1738030 (Open Web Text)

Max Activating Token Index: 175

Text #18

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.6644. Min Act: -0.1700

Data Index: 427012 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 4.9147. Min Range: -4.9147

Max Act: 4.6563. Min Act: -0.1700

Data Index: 655123 (Open Web Text)

Max Activating Token Index: 909