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

Dataset: Open Web Text

Neuron 822 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: 4.7226. Min Range: -4.7226

Max Act: 4.7226. Min Act: -0.1700

Data Index: 6246121 (Open Web Text)

Max Activating Token Index: 749

Text #1

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.3216. Min Act: -0.1700

Data Index: 6539389 (Open Web Text)

Max Activating Token Index: 710

Text #2

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.2532. Min Act: -0.1700

Data Index: 8564973 (Open Web Text)

Max Activating Token Index: 702

Text #3

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.2160. Min Act: -0.1700

Data Index: 1043764 (Open Web Text)

Max Activating Token Index: 735

Text #4

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.1580. Min Act: -0.1700

Data Index: 8674848 (Open Web Text)

Max Activating Token Index: 707

Text #5

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.1558. Min Act: -0.1700

Data Index: 7167257 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.1378. Min Act: -0.1700

Data Index: 6436918 (Open Web Text)

Max Activating Token Index: 714

Text #7

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.1357. Min Act: -0.1700

Data Index: 5057970 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.0890. Min Act: -0.1700

Data Index: 1560565 (Open Web Text)

Max Activating Token Index: 707

Text #9

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.0565. Min Act: -0.1700

Data Index: 5533277 (Open Web Text)

Max Activating Token Index: 758

Text #10

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.0682. Min Act: -0.1700

Data Index: 6109375 (Open Web Text)

Max Activating Token Index: 704

Text #11

Max Range: 4.7226. Min Range: -4.7226

Max Act: 4.0552. Min Act: -0.1700

Data Index: 7588006 (Open Web Text)

Max Activating Token Index: 765

Text #12

Max Range: 4.7226. Min Range: -4.7226

Max Act: 3.9644. Min Act: -0.1700

Data Index: 2568468 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 4.7226. Min Range: -4.7226

Max Act: 3.9581. Min Act: -0.1700

Data Index: 1195415 (Open Web Text)

Max Activating Token Index: 774

Text #14

Max Range: 4.7226. Min Range: -4.7226

Max Act: 3.8960. Min Act: -0.1700

Data Index: 4903080 (Open Web Text)

Max Activating Token Index: 700

Text #15

Max Range: 4.7226. Min Range: -4.7226

Max Act: 3.9349. Min Act: -0.1700

Data Index: 4477764 (Open Web Text)

Max Activating Token Index: 781

Text #16

Max Range: 4.7226. Min Range: -4.7226

Max Act: 3.8819. Min Act: -0.1700

Data Index: 7584848 (Open Web Text)

Max Activating Token Index: 720

Text #17

Max Range: 4.7226. Min Range: -4.7226

Max Act: 3.8871. Min Act: -0.1700

Data Index: 5215243 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 4.7226. Min Range: -4.7226

Max Act: 3.8802. Min Act: -0.1700

Data Index: 5456900 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 4.7226. Min Range: -4.7226

Max Act: 3.8513. Min Act: -0.1700

Data Index: 3452672 (Open Web Text)

Max Activating Token Index: 669