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

Dataset: Open Web Text

Neuron 2865 in Layer 5

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: 4.0743. Min Range: -4.0743

Max Act: 4.0743. Min Act: -0.1700

Data Index: 1741509 (Open Web Text)

Max Activating Token Index: 732

Text #1

Max Range: 4.0743. Min Range: -4.0743

Max Act: 4.0108. Min Act: -0.1700

Data Index: 4098588 (Open Web Text)

Max Activating Token Index: 752

Text #2

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.9456. Min Act: -0.1700

Data Index: 6127466 (Open Web Text)

Max Activating Token Index: 941

Text #3

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.9066. Min Act: -0.1700

Data Index: 1425081 (Open Web Text)

Max Activating Token Index: 628

Text #4

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.9013. Min Act: -0.1700

Data Index: 1351882 (Open Web Text)

Max Activating Token Index: 918

Text #5

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.8398. Min Act: -0.1700

Data Index: 4764552 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.8671. Min Act: -0.1700

Data Index: 5734121 (Open Web Text)

Max Activating Token Index: 860

Text #7

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7991. Min Act: -0.1700

Data Index: 2839768 (Open Web Text)

Max Activating Token Index: 990

Text #8

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.8504. Min Act: -0.1700

Data Index: 6712629 (Open Web Text)

Max Activating Token Index: 808

Text #9

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7794. Min Act: -0.1700

Data Index: 3167323 (Open Web Text)

Max Activating Token Index: 323

Text #10

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7987. Min Act: -0.1700

Data Index: 2395571 (Open Web Text)

Max Activating Token Index: 814

Text #11

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7164. Min Act: -0.1700

Data Index: 8720069 (Open Web Text)

Max Activating Token Index: 589

Text #12

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7670. Min Act: -0.1700

Data Index: 863068 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7716. Min Act: -0.1700

Data Index: 30887 (Open Web Text)

Max Activating Token Index: 723

Text #14

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7345. Min Act: -0.1700

Data Index: 934999 (Open Web Text)

Max Activating Token Index: 216

Text #15

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7686. Min Act: -0.1700

Data Index: 2098430 (Open Web Text)

Max Activating Token Index: 145

Text #16

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7486. Min Act: -0.1700

Data Index: 671064 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7391. Min Act: -0.1700

Data Index: 5006827 (Open Web Text)

Max Activating Token Index: 132

Text #18

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7156. Min Act: -0.1700

Data Index: 5538354 (Open Web Text)

Max Activating Token Index: 303

Text #19

Max Range: 4.0743. Min Range: -4.0743

Max Act: 3.7377. Min Act: -0.1700

Data Index: 259095 (Open Web Text)

Max Activating Token Index: 1008