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

Dataset: Open Web Text

Neuron 838 in Layer 4

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: 4.8113. Min Range: -4.8113

Max Act: 4.7877. Min Act: -0.1700

Data Index: 1020725 (Open Web Text)

Max Activating Token Index: 420

Text #1

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.8113. Min Act: -0.1700

Data Index: 6962219 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.7239. Min Act: -0.1700

Data Index: 2596106 (Open Web Text)

Max Activating Token Index: 441

Text #3

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.7637. Min Act: -0.1700

Data Index: 1712536 (Open Web Text)

Max Activating Token Index: 706

Text #4

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.7937. Min Act: -0.1700

Data Index: 5208674 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.7460. Min Act: -0.1700

Data Index: 3249215 (Open Web Text)

Max Activating Token Index: 396

Text #6

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.7301. Min Act: -0.1700

Data Index: 515612 (Open Web Text)

Max Activating Token Index: 344

Text #7

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.7135. Min Act: -0.1700

Data Index: 4514245 (Open Web Text)

Max Activating Token Index: 805

Text #8

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6905. Min Act: -0.1700

Data Index: 8554883 (Open Web Text)

Max Activating Token Index: 456

Text #9

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.7217. Min Act: -0.1700

Data Index: 631974 (Open Web Text)

Max Activating Token Index: 544

Text #10

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.7017. Min Act: -0.1700

Data Index: 5249356 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6999. Min Act: -0.1700

Data Index: 4063790 (Open Web Text)

Max Activating Token Index: 807

Text #12

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6576. Min Act: -0.1700

Data Index: 5084775 (Open Web Text)

Max Activating Token Index: 647

Text #13

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6555. Min Act: -0.1700

Data Index: 3324543 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6848. Min Act: -0.1700

Data Index: 6497447 (Open Web Text)

Max Activating Token Index: 439

Text #15

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6134. Min Act: -0.1700

Data Index: 1197008 (Open Web Text)

Max Activating Token Index: 478

Text #16

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6340. Min Act: -0.1700

Data Index: 5569505 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6340. Min Act: -0.1700

Data Index: 3460360 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6430. Min Act: -0.1700

Data Index: 2747717 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 4.8113. Min Range: -4.8113

Max Act: 4.6649. Min Act: -0.1700

Data Index: 2408610 (Open Web Text)

Max Activating Token Index: 499