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

Dataset: Open Web Text

Neuron 734 in Layer 6

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: 6.0498. Min Range: -6.0498

Max Act: 6.0498. Min Act: -0.1700

Data Index: 971445 (Open Web Text)

Max Activating Token Index: 506

Text #1

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.9880. Min Act: -0.1700

Data Index: 1340231 (Open Web Text)

Max Activating Token Index: 909

Text #2

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.9248. Min Act: -0.1700

Data Index: 7515543 (Open Web Text)

Max Activating Token Index: 812

Text #3

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.9315. Min Act: -0.1700

Data Index: 5824906 (Open Web Text)

Max Activating Token Index: 419

Text #4

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.8847. Min Act: -0.1700

Data Index: 3801331 (Open Web Text)

Max Activating Token Index: 319

Text #5

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.8100. Min Act: -0.1700

Data Index: 4993433 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7892. Min Act: -0.1700

Data Index: 6299407 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.8484. Min Act: -0.1700

Data Index: 217889 (Open Web Text)

Max Activating Token Index: 771

Text #8

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.8221. Min Act: -0.1700

Data Index: 7582479 (Open Web Text)

Max Activating Token Index: 921

Text #9

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7169. Min Act: -0.1700

Data Index: 5132808 (Open Web Text)

Max Activating Token Index: 779

Text #10

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7385. Min Act: -0.1700

Data Index: 647617 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7353. Min Act: -0.1700

Data Index: 4777271 (Open Web Text)

Max Activating Token Index: 307

Text #12

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7371. Min Act: -0.1700

Data Index: 6491888 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7326. Min Act: -0.1700

Data Index: 6124502 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7137. Min Act: -0.1700

Data Index: 2461062 (Open Web Text)

Max Activating Token Index: 672

Text #15

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7415. Min Act: -0.1700

Data Index: 585552 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.7145. Min Act: -0.1700

Data Index: 2915043 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.6834. Min Act: -0.1700

Data Index: 5042025 (Open Web Text)

Max Activating Token Index: 174

Text #18

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.6544. Min Act: -0.1700

Data Index: 4630152 (Open Web Text)

Max Activating Token Index: 1010

Text #19

Max Range: 6.0498. Min Range: -6.0498

Max Act: 5.6862. Min Act: -0.1700

Data Index: 3811570 (Open Web Text)

Max Activating Token Index: 155