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

Dataset: Open Web Text

Neuron 2995 in Layer 1

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: 1.0270. Min Range: -1.0270

Max Act: 1.0213. Min Act: -0.1655

Data Index: 2805912 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0270. Min Act: -0.1604

Data Index: 4100248 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0210. Min Act: -0.1534

Data Index: 8805551 (Open Web Text)

Max Activating Token Index: 776

Text #3

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0210. Min Act: -0.1653

Data Index: 2444656 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0116. Min Act: -0.1610

Data Index: 3038954 (Open Web Text)

Max Activating Token Index: 872

Text #5

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0125. Min Act: -0.1654

Data Index: 543027 (Open Web Text)

Max Activating Token Index: 549

Text #6

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0099. Min Act: -0.1575

Data Index: 2282444 (Open Web Text)

Max Activating Token Index: 766

Text #7

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9979. Min Act: -0.1513

Data Index: 6361764 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0022. Min Act: -0.1461

Data Index: 6120039 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9993. Min Act: -0.1626

Data Index: 5324018 (Open Web Text)

Max Activating Token Index: 769

Text #10

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9911. Min Act: -0.1629

Data Index: 3114320 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9861. Min Act: -0.1681

Data Index: 8445543 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9910. Min Act: -0.1597

Data Index: 6418262 (Open Web Text)

Max Activating Token Index: 328

Text #13

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9849. Min Act: -0.1610

Data Index: 7739977 (Open Web Text)

Max Activating Token Index: 592

Text #14

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9876. Min Act: -0.1698

Data Index: 6610237 (Open Web Text)

Max Activating Token Index: 644

Text #15

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9790. Min Act: -0.1679

Data Index: 3836083 (Open Web Text)

Max Activating Token Index: 759

Text #16

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9850. Min Act: -0.1605

Data Index: 6476152 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9791. Min Act: -0.1607

Data Index: 86560 (Open Web Text)

Max Activating Token Index: 293

Text #18

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9743. Min Act: -0.1604

Data Index: 203957 (Open Web Text)

Max Activating Token Index: 510

Text #19

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9776. Min Act: -0.1615

Data Index: 2166476 (Open Web Text)

Max Activating Token Index: 715