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

Dataset: Open Web Text

Neuron 1898 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: 3.2264. Min Range: -3.2264

Max Act: 3.2264. Min Act: -0.1700

Data Index: 553317 (Open Web Text)

Max Activating Token Index: 836

Text #1

Max Range: 3.2264. Min Range: -3.2264

Max Act: 3.0979. Min Act: -0.1700

Data Index: 7003681 (Open Web Text)

Max Activating Token Index: 478

Text #2

Max Range: 3.2264. Min Range: -3.2264

Max Act: 3.1678. Min Act: -0.1700

Data Index: 6908949 (Open Web Text)

Max Activating Token Index: 435

Text #3

Max Range: 3.2264. Min Range: -3.2264

Max Act: 3.0583. Min Act: -0.1700

Data Index: 5118800 (Open Web Text)

Max Activating Token Index: 742

Text #4

Max Range: 3.2264. Min Range: -3.2264

Max Act: 3.0218. Min Act: -0.1700

Data Index: 3676319 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 3.2264. Min Range: -3.2264

Max Act: 3.0312. Min Act: -0.1700

Data Index: 8665491 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 3.2264. Min Range: -3.2264

Max Act: 3.0371. Min Act: -0.1700

Data Index: 2984884 (Open Web Text)

Max Activating Token Index: 609

Text #7

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9844. Min Act: -0.1700

Data Index: 322314 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9917. Min Act: -0.1700

Data Index: 4240600 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 3.2264. Min Range: -3.2264

Max Act: 3.0103. Min Act: -0.1700

Data Index: 760521 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 3.2264. Min Range: -3.2264

Max Act: 3.0108. Min Act: -0.1700

Data Index: 1564121 (Open Web Text)

Max Activating Token Index: 833

Text #11

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9681. Min Act: -0.1700

Data Index: 2962342 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9805. Min Act: -0.1700

Data Index: 3748245 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9824. Min Act: -0.1700

Data Index: 4543873 (Open Web Text)

Max Activating Token Index: 921

Text #14

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9589. Min Act: -0.1700

Data Index: 4777116 (Open Web Text)

Max Activating Token Index: 772

Text #15

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9660. Min Act: -0.1700

Data Index: 7444650 (Open Web Text)

Max Activating Token Index: 291

Text #16

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9683. Min Act: -0.1700

Data Index: 5835147 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9521. Min Act: -0.1700

Data Index: 8519414 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9667. Min Act: -0.1700

Data Index: 5520666 (Open Web Text)

Max Activating Token Index: 266

Text #19

Max Range: 3.2264. Min Range: -3.2264

Max Act: 2.9360. Min Act: -0.1700

Data Index: 1864580 (Open Web Text)

Max Activating Token Index: 222