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

Dataset: Open Web Text

Neuron 1985 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: 5.3368. Min Range: -5.3368

Max Act: 5.3368. Min Act: -0.1700

Data Index: 1910315 (Open Web Text)

Max Activating Token Index: 732

Text #1

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.2666. Min Act: -0.1700

Data Index: 3822048 (Open Web Text)

Max Activating Token Index: 844

Text #2

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.2404. Min Act: -0.1700

Data Index: 2923881 (Open Web Text)

Max Activating Token Index: 713

Text #3

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.1836. Min Act: -0.1700

Data Index: 4993186 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.0886. Min Act: -0.1700

Data Index: 78003 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.2812. Min Act: -0.1700

Data Index: 8315011 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.1020. Min Act: -0.1700

Data Index: 7274547 (Open Web Text)

Max Activating Token Index: 685

Text #7

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.3042. Min Act: -0.1700

Data Index: 6699833 (Open Web Text)

Max Activating Token Index: 661

Text #8

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.2488. Min Act: -0.1700

Data Index: 3502525 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.2106. Min Act: -0.1700

Data Index: 6220102 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.1996. Min Act: -0.1700

Data Index: 1810854 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.2426. Min Act: -0.1700

Data Index: 7206208 (Open Web Text)

Max Activating Token Index: 699

Text #12

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.1498. Min Act: -0.1700

Data Index: 607874 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.3292. Min Act: -0.1700

Data Index: 4620461 (Open Web Text)

Max Activating Token Index: 737

Text #14

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.1003. Min Act: -0.1700

Data Index: 2792570 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.0973. Min Act: -0.1700

Data Index: 223533 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.1016. Min Act: -0.1700

Data Index: 6569134 (Open Web Text)

Max Activating Token Index: 822

Text #17

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.1540. Min Act: -0.1700

Data Index: 6655763 (Open Web Text)

Max Activating Token Index: 742

Text #18

Max Range: 5.3368. Min Range: -5.3368

Max Act: 5.0811. Min Act: -0.1700

Data Index: 3429284 (Open Web Text)

Max Activating Token Index: 746

Text #19

Max Range: 5.3368. Min Range: -5.3368

Max Act: 4.8689. Min Act: -0.1700

Data Index: 7516108 (Open Web Text)

Max Activating Token Index: 426