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

Dataset: Open Web Text

Neuron 1858 in Layer 5

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: 4.5740. Min Range: -4.5740

Max Act: 4.5740. Min Act: -0.1700

Data Index: 547487 (Open Web Text)

Max Activating Token Index: 702

Text #1

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.5345. Min Act: -0.1700

Data Index: 2214996 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.5236. Min Act: -0.1700

Data Index: 3913583 (Open Web Text)

Max Activating Token Index: 317

Text #3

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4930. Min Act: -0.1700

Data Index: 393896 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4637. Min Act: -0.1700

Data Index: 3445524 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4708. Min Act: -0.1700

Data Index: 6487238 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4477. Min Act: -0.1700

Data Index: 5160855 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4432. Min Act: -0.1700

Data Index: 3076532 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4509. Min Act: -0.1700

Data Index: 3320263 (Open Web Text)

Max Activating Token Index: 704

Text #9

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4372. Min Act: -0.1700

Data Index: 8247851 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4278. Min Act: -0.1700

Data Index: 4653097 (Open Web Text)

Max Activating Token Index: 642

Text #11

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4389. Min Act: -0.1700

Data Index: 2657898 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4029. Min Act: -0.1700

Data Index: 3631938 (Open Web Text)

Max Activating Token Index: 291

Text #13

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4138. Min Act: -0.1700

Data Index: 5145345 (Open Web Text)

Max Activating Token Index: 489

Text #14

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4201. Min Act: -0.1700

Data Index: 5731000 (Open Web Text)

Max Activating Token Index: 571

Text #15

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4037. Min Act: -0.1700

Data Index: 3385944 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4107. Min Act: -0.1700

Data Index: 8474391 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.3630. Min Act: -0.1700

Data Index: 8301819 (Open Web Text)

Max Activating Token Index: 573

Text #18

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.4077. Min Act: -0.1700

Data Index: 4273593 (Open Web Text)

Max Activating Token Index: 490

Text #19

Max Range: 4.5740. Min Range: -4.5740

Max Act: 4.3696. Min Act: -0.1700

Data Index: 2110374 (Open Web Text)

Max Activating Token Index: 506