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

Dataset: Open Web Text

Neuron 2949 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: 2.8837. Min Range: -2.8837

Max Act: 2.8837. Min Act: -0.1700

Data Index: 627819 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.8040. Min Act: -0.1700

Data Index: 4360585 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.7807. Min Act: -0.1700

Data Index: 1713484 (Open Web Text)

Max Activating Token Index: 947

Text #3

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.7763. Min Act: -0.1700

Data Index: 5810207 (Open Web Text)

Max Activating Token Index: 109

Text #4

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.7642. Min Act: -0.1700

Data Index: 3308494 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.7725. Min Act: -0.1700

Data Index: 4632879 (Open Web Text)

Max Activating Token Index: 197

Text #6

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.7270. Min Act: -0.1700

Data Index: 2594775 (Open Web Text)

Max Activating Token Index: 127

Text #7

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6910. Min Act: -0.1700

Data Index: 3628294 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.7108. Min Act: -0.1700

Data Index: 7421839 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6871. Min Act: -0.1700

Data Index: 6084590 (Open Web Text)

Max Activating Token Index: 171

Text #10

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6887. Min Act: -0.1700

Data Index: 4664689 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6768. Min Act: -0.1700

Data Index: 8590583 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6777. Min Act: -0.1700

Data Index: 48831 (Open Web Text)

Max Activating Token Index: 677

Text #13

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6879. Min Act: -0.1700

Data Index: 3046257 (Open Web Text)

Max Activating Token Index: 322

Text #14

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6679. Min Act: -0.1700

Data Index: 8221096 (Open Web Text)

Max Activating Token Index: 723

Text #15

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6536. Min Act: -0.1700

Data Index: 883454 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6612. Min Act: -0.1700

Data Index: 566781 (Open Web Text)

Max Activating Token Index: 627

Text #17

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6509. Min Act: -0.1700

Data Index: 2619480 (Open Web Text)

Max Activating Token Index: 674

Text #18

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6630. Min Act: -0.1700

Data Index: 2653585 (Open Web Text)

Max Activating Token Index: 757

Text #19

Max Range: 2.8837. Min Range: -2.8837

Max Act: 2.6532. Min Act: -0.1700

Data Index: 6419612 (Open Web Text)

Max Activating Token Index: 717