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

Dataset: Open Web Text

Neuron 2200 in Layer 1

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: 0.8137. Min Range: -0.8137

Max Act: 0.8137. Min Act: -0.1700

Data Index: 6555067 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.8093. Min Act: -0.1700

Data Index: 717713 (Open Web Text)

Max Activating Token Index: 759

Text #2

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.8035. Min Act: -0.1700

Data Index: 937410 (Open Web Text)

Max Activating Token Index: 734

Text #3

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.8055. Min Act: -0.1700

Data Index: 2465003 (Open Web Text)

Max Activating Token Index: 747

Text #4

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.8061. Min Act: -0.1700

Data Index: 8438876 (Open Web Text)

Max Activating Token Index: 744

Text #5

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7889. Min Act: -0.1700

Data Index: 5673721 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7788. Min Act: -0.1700

Data Index: 3750682 (Open Web Text)

Max Activating Token Index: 756

Text #7

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7752. Min Act: -0.1700

Data Index: 1199203 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7732. Min Act: -0.1700

Data Index: 8438884 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7689. Min Act: -0.1700

Data Index: 8438874 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7721. Min Act: -0.1700

Data Index: 6709991 (Open Web Text)

Max Activating Token Index: 754

Text #11

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7685. Min Act: -0.1700

Data Index: 5666569 (Open Web Text)

Max Activating Token Index: 764

Text #12

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7645. Min Act: -0.1700

Data Index: 198640 (Open Web Text)

Max Activating Token Index: 765

Text #13

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7572. Min Act: -0.1700

Data Index: 7465432 (Open Web Text)

Max Activating Token Index: 741

Text #14

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7566. Min Act: -0.1700

Data Index: 1733706 (Open Web Text)

Max Activating Token Index: 774

Text #15

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7614. Min Act: -0.1700

Data Index: 8438883 (Open Web Text)

Max Activating Token Index: 743

Text #16

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7636. Min Act: -0.1700

Data Index: 4331430 (Open Web Text)

Max Activating Token Index: 755

Text #17

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7534. Min Act: -0.1700

Data Index: 5486769 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7475. Min Act: -0.1700

Data Index: 7865674 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 0.8137. Min Range: -0.8137

Max Act: 0.7520. Min Act: -0.1700

Data Index: 3134382 (Open Web Text)

Max Activating Token Index: 764