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

Dataset: Open Web Text

Neuron 2738 in Layer 2

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: 1.5829. Min Range: -1.5829

Max Act: 1.5829. Min Act: -0.1698

Data Index: 1046107 (Open Web Text)

Max Activating Token Index: 297

Text #1

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5718. Min Act: -0.1700

Data Index: 2274145 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5642. Min Act: -0.1699

Data Index: 7627731 (Open Web Text)

Max Activating Token Index: 752

Text #3

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5666. Min Act: -0.1700

Data Index: 1775112 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5603. Min Act: -0.1687

Data Index: 3293279 (Open Web Text)

Max Activating Token Index: 845

Text #5

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5392. Min Act: -0.1699

Data Index: 7128453 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5511. Min Act: -0.1700

Data Index: 1412722 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5383. Min Act: -0.1700

Data Index: 3661638 (Open Web Text)

Max Activating Token Index: 691

Text #8

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5402. Min Act: -0.1700

Data Index: 8497603 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5216. Min Act: -0.1700

Data Index: 5205919 (Open Web Text)

Max Activating Token Index: 967

Text #10

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5298. Min Act: -0.1700

Data Index: 3065627 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5381. Min Act: -0.1692

Data Index: 2168723 (Open Web Text)

Max Activating Token Index: 870

Text #12

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5215. Min Act: -0.1698

Data Index: 8655686 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5328. Min Act: -0.1700

Data Index: 3795489 (Open Web Text)

Max Activating Token Index: 241

Text #14

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5204. Min Act: -0.1700

Data Index: 2809218 (Open Web Text)

Max Activating Token Index: 773

Text #15

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5220. Min Act: -0.1695

Data Index: 3006325 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5098. Min Act: -0.1698

Data Index: 5683305 (Open Web Text)

Max Activating Token Index: 345

Text #17

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5166. Min Act: -0.1700

Data Index: 6932084 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5196. Min Act: -0.1700

Data Index: 8129701 (Open Web Text)

Max Activating Token Index: 222

Text #19

Max Range: 1.5829. Min Range: -1.5829

Max Act: 1.5089. Min Act: -0.1700

Data Index: 7627732 (Open Web Text)

Max Activating Token Index: 268