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

Dataset: Open Web Text

Neuron 2829 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: 1.8452. Min Range: -1.8452

Max Act: 1.8452. Min Act: -0.1700

Data Index: 3191306 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.8290. Min Act: -0.1700

Data Index: 8642949 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.8392. Min Act: -0.1700

Data Index: 7413416 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.8210. Min Act: -0.1700

Data Index: 1306359 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.8090. Min Act: -0.1700

Data Index: 7276961 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7785. Min Act: -0.1700

Data Index: 7029771 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7474. Min Act: -0.1700

Data Index: 1792631 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7487. Min Act: -0.1700

Data Index: 1298536 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7323. Min Act: -0.1700

Data Index: 7123761 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7303. Min Act: -0.1700

Data Index: 6761831 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7262. Min Act: -0.1700

Data Index: 1311216 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7253. Min Act: -0.1700

Data Index: 531212 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7239. Min Act: -0.1700

Data Index: 1627411 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7117. Min Act: -0.1700

Data Index: 8718659 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7173. Min Act: -0.1700

Data Index: 1853178 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7155. Min Act: -0.1700

Data Index: 1636844 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7029. Min Act: -0.1700

Data Index: 8008357 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.6936. Min Act: -0.1700

Data Index: 832168 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.7075. Min Act: -0.1700

Data Index: 2507943 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 1.8452. Min Range: -1.8452

Max Act: 1.6994. Min Act: -0.1700

Data Index: 2760119 (Open Web Text)

Max Activating Token Index: 21