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

Dataset: Open Web Text

Neuron 2687 in Layer 3

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: 4.7044. Min Range: -4.7044

Max Act: 4.6784. Min Act: -0.1700

Data Index: 956948 (Open Web Text)

Max Activating Token Index: 45

Text #1

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6348. Min Act: -0.1700

Data Index: 7475381 (Open Web Text)

Max Activating Token Index: 223

Text #2

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.7044. Min Act: -0.1700

Data Index: 2706619 (Open Web Text)

Max Activating Token Index: 987

Text #3

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6440. Min Act: -0.1700

Data Index: 6193385 (Open Web Text)

Max Activating Token Index: 35

Text #4

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6710. Min Act: -0.1700

Data Index: 6494015 (Open Web Text)

Max Activating Token Index: 934

Text #5

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6365. Min Act: -0.1700

Data Index: 1801566 (Open Web Text)

Max Activating Token Index: 570

Text #6

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6162. Min Act: -0.1700

Data Index: 7654365 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6361. Min Act: -0.1700

Data Index: 2233734 (Open Web Text)

Max Activating Token Index: 820

Text #8

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6093. Min Act: -0.1700

Data Index: 6874279 (Open Web Text)

Max Activating Token Index: 512

Text #9

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6695. Min Act: -0.1700

Data Index: 6299759 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6106. Min Act: -0.1700

Data Index: 3012570 (Open Web Text)

Max Activating Token Index: 917

Text #11

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6075. Min Act: -0.1700

Data Index: 5737994 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.5829. Min Act: -0.1700

Data Index: 328204 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6523. Min Act: -0.1700

Data Index: 5053257 (Open Web Text)

Max Activating Token Index: 428

Text #14

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.5973. Min Act: -0.1700

Data Index: 727565 (Open Web Text)

Max Activating Token Index: 479

Text #15

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6017. Min Act: -0.1700

Data Index: 1396505 (Open Web Text)

Max Activating Token Index: 971

Text #16

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6004. Min Act: -0.1700

Data Index: 1397245 (Open Web Text)

Max Activating Token Index: 859

Text #17

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.6029. Min Act: -0.1700

Data Index: 1290069 (Open Web Text)

Max Activating Token Index: 807

Text #18

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.5607. Min Act: -0.1700

Data Index: 7128307 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 4.7044. Min Range: -4.7044

Max Act: 4.5561. Min Act: -0.1700

Data Index: 408760 (Open Web Text)

Max Activating Token Index: 938