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

Dataset: Open Web Text

Neuron 940 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: 1.8692. Min Range: -1.8692

Max Act: 1.8692. Min Act: -0.1700

Data Index: 5557600 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.8179. Min Act: -0.1700

Data Index: 3180378 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.8001. Min Act: -0.1700

Data Index: 2377974 (Open Web Text)

Max Activating Token Index: 543

Text #3

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7587. Min Act: -0.1700

Data Index: 3914281 (Open Web Text)

Max Activating Token Index: 779

Text #4

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7622. Min Act: -0.1700

Data Index: 6519093 (Open Web Text)

Max Activating Token Index: 346

Text #5

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7243. Min Act: -0.1700

Data Index: 5563110 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7121. Min Act: -0.1700

Data Index: 1789680 (Open Web Text)

Max Activating Token Index: 312

Text #7

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7039. Min Act: -0.1700

Data Index: 4139860 (Open Web Text)

Max Activating Token Index: 1001

Text #8

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6966. Min Act: -0.1700

Data Index: 871113 (Open Web Text)

Max Activating Token Index: 922

Text #9

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6876. Min Act: -0.1700

Data Index: 5390599 (Open Web Text)

Max Activating Token Index: 773

Text #10

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6731. Min Act: -0.1700

Data Index: 6814838 (Open Web Text)

Max Activating Token Index: 950

Text #11

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6779. Min Act: -0.1700

Data Index: 1512035 (Open Web Text)

Max Activating Token Index: 240

Text #12

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6681. Min Act: -0.1700

Data Index: 5536912 (Open Web Text)

Max Activating Token Index: 792

Text #13

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6809. Min Act: -0.1700

Data Index: 4776344 (Open Web Text)

Max Activating Token Index: 1012

Text #14

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6293. Min Act: -0.1700

Data Index: 758758 (Open Web Text)

Max Activating Token Index: 360

Text #15

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6569. Min Act: -0.1700

Data Index: 3209622 (Open Web Text)

Max Activating Token Index: 760

Text #16

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6767. Min Act: -0.1700

Data Index: 3414830 (Open Web Text)

Max Activating Token Index: 655

Text #17

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6650. Min Act: -0.1700

Data Index: 2076337 (Open Web Text)

Max Activating Token Index: 199

Text #18

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6491. Min Act: -0.1700

Data Index: 2124258 (Open Web Text)

Max Activating Token Index: 510

Text #19

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.6532. Min Act: -0.1700

Data Index: 3667891 (Open Web Text)

Max Activating Token Index: 432