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

Dataset: Open Web Text

Neuron 1753 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: 3.7906. Min Range: -3.7906

Max Act: 3.7670. Min Act: -0.1700

Data Index: 6671443 (Open Web Text)

Max Activating Token Index: 867

Text #1

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.7906. Min Act: -0.1700

Data Index: 1614526 (Open Web Text)

Max Activating Token Index: 627

Text #2

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.7206. Min Act: -0.1700

Data Index: 6542055 (Open Web Text)

Max Activating Token Index: 276

Text #3

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.7393. Min Act: -0.1700

Data Index: 4469404 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.6594. Min Act: -0.1700

Data Index: 4699417 (Open Web Text)

Max Activating Token Index: 998

Text #5

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.6668. Min Act: -0.1700

Data Index: 2044825 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5728. Min Act: -0.1700

Data Index: 1199893 (Open Web Text)

Max Activating Token Index: 278

Text #7

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.6135. Min Act: -0.1700

Data Index: 4969880 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.6415. Min Act: -0.1700

Data Index: 7913611 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5920. Min Act: -0.1700

Data Index: 4259305 (Open Web Text)

Max Activating Token Index: 354

Text #10

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.6233. Min Act: -0.1700

Data Index: 319385 (Open Web Text)

Max Activating Token Index: 594

Text #11

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5560. Min Act: -0.1700

Data Index: 3480412 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.6384. Min Act: -0.1700

Data Index: 5603117 (Open Web Text)

Max Activating Token Index: 738

Text #13

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5344. Min Act: -0.1700

Data Index: 2857061 (Open Web Text)

Max Activating Token Index: 353

Text #14

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.6157. Min Act: -0.1700

Data Index: 8682208 (Open Web Text)

Max Activating Token Index: 994

Text #15

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5655. Min Act: -0.1700

Data Index: 1737638 (Open Web Text)

Max Activating Token Index: 991

Text #16

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5391. Min Act: -0.1700

Data Index: 2534225 (Open Web Text)

Max Activating Token Index: 941

Text #17

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5280. Min Act: -0.1700

Data Index: 8255268 (Open Web Text)

Max Activating Token Index: 793

Text #18

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5292. Min Act: -0.1700

Data Index: 3790433 (Open Web Text)

Max Activating Token Index: 706

Text #19

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.5598. Min Act: -0.1700

Data Index: 3968894 (Open Web Text)

Max Activating Token Index: 606