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

Dataset: Open Web Text

Neuron 1929 in Layer 0

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: 6.8697. Min Range: -6.8697

Max Act: 6.8697. Min Act: -0.1700

Data Index: 6182583 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7947. Min Act: -0.1700

Data Index: 8585590 (Open Web Text)

Max Activating Token Index: 556

Text #2

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7136. Min Act: -0.1700

Data Index: 5552117 (Open Web Text)

Max Activating Token Index: 724

Text #3

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7145. Min Act: -0.1700

Data Index: 7056573 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7131. Min Act: -0.1700

Data Index: 6952173 (Open Web Text)

Max Activating Token Index: 558

Text #5

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7076. Min Act: -0.1700

Data Index: 6662158 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.6879. Min Act: -0.1700

Data Index: 6524004 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7154. Min Act: -0.1700

Data Index: 6237633 (Open Web Text)

Max Activating Token Index: 140

Text #8

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7320. Min Act: -0.1700

Data Index: 1811546 (Open Web Text)

Max Activating Token Index: 655

Text #9

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7297. Min Act: -0.1700

Data Index: 6070372 (Open Web Text)

Max Activating Token Index: 230

Text #10

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7235. Min Act: -0.1700

Data Index: 27823 (Open Web Text)

Max Activating Token Index: 133

Text #11

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7241. Min Act: -0.1700

Data Index: 5089421 (Open Web Text)

Max Activating Token Index: 219

Text #12

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7184. Min Act: -0.1700

Data Index: 890777 (Open Web Text)

Max Activating Token Index: 702

Text #13

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.6975. Min Act: -0.1700

Data Index: 3794010 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7188. Min Act: -0.1700

Data Index: 3310403 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7178. Min Act: -0.1700

Data Index: 866404 (Open Web Text)

Max Activating Token Index: 715

Text #16

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7109. Min Act: -0.1700

Data Index: 2787184 (Open Web Text)

Max Activating Token Index: 659

Text #17

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7069. Min Act: -0.1700

Data Index: 480948 (Open Web Text)

Max Activating Token Index: 667

Text #18

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.7323. Min Act: -0.1700

Data Index: 422084 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 6.8697. Min Range: -6.8697

Max Act: 6.6907. Min Act: -0.1700

Data Index: 2527912 (Open Web Text)

Max Activating Token Index: 705