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

Dataset: Open Web Text

Neuron 423 in Layer 1

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: 1.7095. Min Range: -1.7095

Max Act: 1.7095. Min Act: -0.1700

Data Index: 6541906 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6837. Min Act: -0.1700

Data Index: 6992566 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6790. Min Act: -0.1698

Data Index: 3528716 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6734. Min Act: -0.1700

Data Index: 4154623 (Open Web Text)

Max Activating Token Index: 692

Text #4

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6664. Min Act: -0.1700

Data Index: 4551480 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6605. Min Act: -0.1700

Data Index: 7525317 (Open Web Text)

Max Activating Token Index: 66

Text #6

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6580. Min Act: -0.1700

Data Index: 4515030 (Open Web Text)

Max Activating Token Index: 71

Text #7

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6647. Min Act: -0.1700

Data Index: 1869269 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6590. Min Act: -0.1700

Data Index: 7658810 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6556. Min Act: -0.1700

Data Index: 4267195 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6588. Min Act: -0.1700

Data Index: 1676539 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6491. Min Act: -0.1700

Data Index: 5919544 (Open Web Text)

Max Activating Token Index: 592

Text #12

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6392. Min Act: -0.1699

Data Index: 6014611 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6378. Min Act: -0.1700

Data Index: 3390531 (Open Web Text)

Max Activating Token Index: 530

Text #14

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6284. Min Act: -0.1699

Data Index: 490225 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6468. Min Act: -0.1700

Data Index: 3507927 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6466. Min Act: -0.1700

Data Index: 5081311 (Open Web Text)

Max Activating Token Index: 354

Text #17

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6353. Min Act: -0.1700

Data Index: 6754282 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6314. Min Act: -0.1700

Data Index: 647889 (Open Web Text)

Max Activating Token Index: 372

Text #19

Max Range: 1.7095. Min Range: -1.7095

Max Act: 1.6243. Min Act: -0.1700

Data Index: 1813171 (Open Web Text)

Max Activating Token Index: 738