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

Dataset: Open Web Text

Neuron 3015 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: 1.4869. Min Range: -1.4869

Max Act: 1.4869. Min Act: -0.1700

Data Index: 6778774 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4680. Min Act: -0.1700

Data Index: 7642741 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4655. Min Act: -0.1700

Data Index: 4739697 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4675. Min Act: -0.1700

Data Index: 7498401 (Open Web Text)

Max Activating Token Index: 286

Text #4

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4677. Min Act: -0.1675

Data Index: 1384119 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4617. Min Act: -0.1598

Data Index: 4119073 (Open Web Text)

Max Activating Token Index: 894

Text #6

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4469. Min Act: -0.1699

Data Index: 3824312 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4507. Min Act: -0.1593

Data Index: 5540474 (Open Web Text)

Max Activating Token Index: 151

Text #8

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4391. Min Act: -0.1700

Data Index: 1464917 (Open Web Text)

Max Activating Token Index: 482

Text #9

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4377. Min Act: -0.1700

Data Index: 2268054 (Open Web Text)

Max Activating Token Index: 747

Text #10

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4372. Min Act: -0.1700

Data Index: 7423009 (Open Web Text)

Max Activating Token Index: 195

Text #11

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4381. Min Act: -0.1690

Data Index: 1275387 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4339. Min Act: -0.1700

Data Index: 2780345 (Open Web Text)

Max Activating Token Index: 448

Text #13

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4390. Min Act: -0.1700

Data Index: 3992142 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4401. Min Act: -0.1700

Data Index: 8321760 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4321. Min Act: -0.1677

Data Index: 1583852 (Open Web Text)

Max Activating Token Index: 351

Text #16

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4316. Min Act: -0.1700

Data Index: 5966263 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4338. Min Act: -0.1700

Data Index: 5409002 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4261. Min Act: -0.1700

Data Index: 423975 (Open Web Text)

Max Activating Token Index: 683

Text #19

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4220. Min Act: -0.1697

Data Index: 6892510 (Open Web Text)

Max Activating Token Index: 1021