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

Dataset: Open Web Text

Neuron 1899 in Layer 4

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: 4.2999. Min Range: -4.2999

Max Act: 4.2999. Min Act: -0.1700

Data Index: 6920404 (Open Web Text)

Max Activating Token Index: 835

Text #1

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.2557. Min Act: -0.1700

Data Index: 6047555 (Open Web Text)

Max Activating Token Index: 305

Text #2

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.1608. Min Act: -0.1700

Data Index: 6617333 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.1572. Min Act: -0.1700

Data Index: 6047554 (Open Web Text)

Max Activating Token Index: 709

Text #4

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.1300. Min Act: -0.1700

Data Index: 1761455 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.1336. Min Act: -0.1700

Data Index: 4745391 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.1129. Min Act: -0.1700

Data Index: 6390305 (Open Web Text)

Max Activating Token Index: 754

Text #7

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.1039. Min Act: -0.1700

Data Index: 2978652 (Open Web Text)

Max Activating Token Index: 38

Text #8

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0877. Min Act: -0.1700

Data Index: 821431 (Open Web Text)

Max Activating Token Index: 406

Text #9

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0734. Min Act: -0.1700

Data Index: 5869187 (Open Web Text)

Max Activating Token Index: 191

Text #10

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0596. Min Act: -0.1700

Data Index: 1183572 (Open Web Text)

Max Activating Token Index: 500

Text #11

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0359. Min Act: -0.1700

Data Index: 6282935 (Open Web Text)

Max Activating Token Index: 46

Text #12

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0181. Min Act: -0.1700

Data Index: 2671794 (Open Web Text)

Max Activating Token Index: 303

Text #13

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0270. Min Act: -0.1700

Data Index: 5510607 (Open Web Text)

Max Activating Token Index: 194

Text #14

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0244. Min Act: -0.1700

Data Index: 2773158 (Open Web Text)

Max Activating Token Index: 462

Text #15

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0113. Min Act: -0.1700

Data Index: 7556403 (Open Web Text)

Max Activating Token Index: 614

Text #16

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0014. Min Act: -0.1700

Data Index: 6435251 (Open Web Text)

Max Activating Token Index: 547

Text #17

Max Range: 4.2999. Min Range: -4.2999

Max Act: 3.9862. Min Act: -0.1700

Data Index: 6911428 (Open Web Text)

Max Activating Token Index: 695

Text #18

Max Range: 4.2999. Min Range: -4.2999

Max Act: 4.0054. Min Act: -0.1700

Data Index: 962753 (Open Web Text)

Max Activating Token Index: 586

Text #19

Max Range: 4.2999. Min Range: -4.2999

Max Act: 3.9736. Min Act: -0.1700

Data Index: 5249505 (Open Web Text)

Max Activating Token Index: 553