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

Dataset: Open Web Text

Neuron 879 in Layer 0

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: 1.7126. Min Range: -1.7126

Max Act: 1.7126. Min Act: -0.1667

Data Index: 4829627 (Open Web Text)

Max Activating Token Index: 329

Text #1

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6880. Min Act: -0.1630

Data Index: 1125065 (Open Web Text)

Max Activating Token Index: 235

Text #2

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6891. Min Act: -0.1699

Data Index: 8674183 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6781. Min Act: -0.1700

Data Index: 4113898 (Open Web Text)

Max Activating Token Index: 334

Text #4

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6677. Min Act: -0.1662

Data Index: 8461495 (Open Web Text)

Max Activating Token Index: 358

Text #5

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6734. Min Act: -0.1700

Data Index: 1484364 (Open Web Text)

Max Activating Token Index: 83

Text #6

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6613. Min Act: -0.1655

Data Index: 609044 (Open Web Text)

Max Activating Token Index: 103

Text #7

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6610. Min Act: -0.1700

Data Index: 3702286 (Open Web Text)

Max Activating Token Index: 247

Text #8

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6624. Min Act: -0.1699

Data Index: 8736682 (Open Web Text)

Max Activating Token Index: 888

Text #9

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6505. Min Act: -0.1644

Data Index: 8461492 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6403. Min Act: -0.1693

Data Index: 6718283 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6427. Min Act: -0.1699

Data Index: 6977885 (Open Web Text)

Max Activating Token Index: 147

Text #12

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6405. Min Act: -0.1689

Data Index: 8073408 (Open Web Text)

Max Activating Token Index: 118

Text #13

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6366. Min Act: -0.1696

Data Index: 2489977 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6336. Min Act: -0.1672

Data Index: 5731769 (Open Web Text)

Max Activating Token Index: 314

Text #15

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6373. Min Act: -0.1698

Data Index: 1792128 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6353. Min Act: -0.1635

Data Index: 4352450 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6324. Min Act: -0.1690

Data Index: 7146574 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6206. Min Act: -0.1618

Data Index: 1981023 (Open Web Text)

Max Activating Token Index: 939

Text #19

Max Range: 1.7126. Min Range: -1.7126

Max Act: 1.6212. Min Act: -0.1699

Data Index: 7257383 (Open Web Text)

Max Activating Token Index: 883