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

Dataset: Open Web Text

Neuron 418 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: 3.8737. Min Range: -3.8737

Max Act: 3.8737. Min Act: -0.1700

Data Index: 4762471 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.4635. Min Act: -0.1700

Data Index: 6636398 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.4547. Min Act: -0.1700

Data Index: 937899 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.3789. Min Act: -0.1700

Data Index: 8598042 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.3190. Min Act: -0.1700

Data Index: 3980551 (Open Web Text)

Max Activating Token Index: 645

Text #5

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.3125. Min Act: -0.1700

Data Index: 4902960 (Open Web Text)

Max Activating Token Index: 638

Text #6

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.3379. Min Act: -0.1700

Data Index: 4387254 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.2726. Min Act: -0.1700

Data Index: 6745722 (Open Web Text)

Max Activating Token Index: 648

Text #8

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.2075. Min Act: -0.1700

Data Index: 1791639 (Open Web Text)

Max Activating Token Index: 926

Text #9

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.2272. Min Act: -0.1700

Data Index: 7494502 (Open Web Text)

Max Activating Token Index: 243

Text #10

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1823. Min Act: -0.1700

Data Index: 3074815 (Open Web Text)

Max Activating Token Index: 675

Text #11

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.2012. Min Act: -0.1700

Data Index: 6368810 (Open Web Text)

Max Activating Token Index: 919

Text #12

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1823. Min Act: -0.1700

Data Index: 8766765 (Open Web Text)

Max Activating Token Index: 885

Text #13

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1712. Min Act: -0.1700

Data Index: 6122854 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1446. Min Act: -0.1700

Data Index: 6542430 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1598. Min Act: -0.1700

Data Index: 7923272 (Open Web Text)

Max Activating Token Index: 846

Text #16

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1180. Min Act: -0.1700

Data Index: 4470686 (Open Web Text)

Max Activating Token Index: 799

Text #17

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1154. Min Act: -0.1700

Data Index: 6989840 (Open Web Text)

Max Activating Token Index: 1011

Text #18

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1550. Min Act: -0.1700

Data Index: 7530659 (Open Web Text)

Max Activating Token Index: 344

Text #19

Max Range: 3.8737. Min Range: -3.8737

Max Act: 3.1405. Min Act: -0.1700

Data Index: 2739768 (Open Web Text)

Max Activating Token Index: 918