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

Dataset: Open Web Text

Neuron 1385 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: 5.2037. Min Range: -5.2037

Max Act: 5.2037. Min Act: -0.1700

Data Index: 7810955 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.1794. Min Act: -0.1700

Data Index: 6649509 (Open Web Text)

Max Activating Token Index: 903

Text #2

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.1220. Min Act: -0.1700

Data Index: 4108363 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.1514. Min Act: -0.1700

Data Index: 555680 (Open Web Text)

Max Activating Token Index: 957

Text #4

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.1139. Min Act: -0.1700

Data Index: 2610736 (Open Web Text)

Max Activating Token Index: 907

Text #5

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.1138. Min Act: -0.1700

Data Index: 648703 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.1214. Min Act: -0.1700

Data Index: 5808476 (Open Web Text)

Max Activating Token Index: 80

Text #7

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0957. Min Act: -0.1700

Data Index: 2472307 (Open Web Text)

Max Activating Token Index: 439

Text #8

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0983. Min Act: -0.1700

Data Index: 7987639 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0797. Min Act: -0.1700

Data Index: 1374763 (Open Web Text)

Max Activating Token Index: 344

Text #10

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0761. Min Act: -0.1700

Data Index: 6016752 (Open Web Text)

Max Activating Token Index: 636

Text #11

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0670. Min Act: -0.1700

Data Index: 8772455 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0612. Min Act: -0.1700

Data Index: 4323943 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0424. Min Act: -0.1700

Data Index: 5507371 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0234. Min Act: -0.1700

Data Index: 5750509 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0410. Min Act: -0.1700

Data Index: 4552320 (Open Web Text)

Max Activating Token Index: 44

Text #16

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0404. Min Act: -0.1700

Data Index: 5919495 (Open Web Text)

Max Activating Token Index: 517

Text #17

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0349. Min Act: -0.1700

Data Index: 923235 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0135. Min Act: -0.1700

Data Index: 1881869 (Open Web Text)

Max Activating Token Index: 947

Text #19

Max Range: 5.2037. Min Range: -5.2037

Max Act: 5.0369. Min Act: -0.1700

Data Index: 6479179 (Open Web Text)

Max Activating Token Index: 470