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

Dataset: Open Web Text

Neuron 2573 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: 4.0260. Min Range: -4.0260

Max Act: 4.0260. Min Act: -0.1700

Data Index: 2366472 (Open Web Text)

Max Activating Token Index: 665

Text #1

Max Range: 4.0260. Min Range: -4.0260

Max Act: 4.0134. Min Act: -0.1700

Data Index: 4701946 (Open Web Text)

Max Activating Token Index: 873

Text #2

Max Range: 4.0260. Min Range: -4.0260

Max Act: 4.0131. Min Act: -0.1700

Data Index: 2405706 (Open Web Text)

Max Activating Token Index: 653

Text #3

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9761. Min Act: -0.1700

Data Index: 1734288 (Open Web Text)

Max Activating Token Index: 818

Text #4

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9751. Min Act: -0.1700

Data Index: 903318 (Open Web Text)

Max Activating Token Index: 394

Text #5

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9432. Min Act: -0.1700

Data Index: 4443708 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9582. Min Act: -0.1700

Data Index: 8829330 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9737. Min Act: -0.1700

Data Index: 2527469 (Open Web Text)

Max Activating Token Index: 486

Text #8

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9380. Min Act: -0.1700

Data Index: 7176400 (Open Web Text)

Max Activating Token Index: 512

Text #9

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9306. Min Act: -0.1700

Data Index: 2001101 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9010. Min Act: -0.1700

Data Index: 6911532 (Open Web Text)

Max Activating Token Index: 104

Text #11

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9225. Min Act: -0.1700

Data Index: 4786258 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9507. Min Act: -0.1700

Data Index: 278103 (Open Web Text)

Max Activating Token Index: 750

Text #13

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9419. Min Act: -0.1700

Data Index: 3374611 (Open Web Text)

Max Activating Token Index: 582

Text #14

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.9060. Min Act: -0.1700

Data Index: 1380230 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.8926. Min Act: -0.1700

Data Index: 2564639 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.8839. Min Act: -0.1700

Data Index: 7956154 (Open Web Text)

Max Activating Token Index: 242

Text #17

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.8438. Min Act: -0.1700

Data Index: 6297348 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.7940. Min Act: -0.1700

Data Index: 4366955 (Open Web Text)

Max Activating Token Index: 530

Text #19

Max Range: 4.0260. Min Range: -4.0260

Max Act: 3.8656. Min Act: -0.1700

Data Index: 6506415 (Open Web Text)

Max Activating Token Index: 453