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

Dataset: Open Web Text

Neuron 1291 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: 4.2295. Min Range: -4.2295

Max Act: 4.2295. Min Act: -0.1700

Data Index: 1359184 (Open Web Text)

Max Activating Token Index: 669

Text #1

Max Range: 4.2295. Min Range: -4.2295

Max Act: 4.0984. Min Act: -0.1700

Data Index: 4813506 (Open Web Text)

Max Activating Token Index: 628

Text #2

Max Range: 4.2295. Min Range: -4.2295

Max Act: 4.1151. Min Act: -0.1700

Data Index: 7775061 (Open Web Text)

Max Activating Token Index: 842

Text #3

Max Range: 4.2295. Min Range: -4.2295

Max Act: 4.0430. Min Act: -0.1700

Data Index: 6986973 (Open Web Text)

Max Activating Token Index: 762

Text #4

Max Range: 4.2295. Min Range: -4.2295

Max Act: 4.0388. Min Act: -0.1700

Data Index: 4748695 (Open Web Text)

Max Activating Token Index: 565

Text #5

Max Range: 4.2295. Min Range: -4.2295

Max Act: 4.0693. Min Act: -0.1700

Data Index: 7310432 (Open Web Text)

Max Activating Token Index: 739

Text #6

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9984. Min Act: -0.1700

Data Index: 8045531 (Open Web Text)

Max Activating Token Index: 755

Text #7

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9862. Min Act: -0.1700

Data Index: 2038450 (Open Web Text)

Max Activating Token Index: 559

Text #8

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9849. Min Act: -0.1700

Data Index: 4020979 (Open Web Text)

Max Activating Token Index: 960

Text #9

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9637. Min Act: -0.1700

Data Index: 5173100 (Open Web Text)

Max Activating Token Index: 802

Text #10

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9544. Min Act: -0.1700

Data Index: 4918345 (Open Web Text)

Max Activating Token Index: 849

Text #11

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9682. Min Act: -0.1700

Data Index: 7458003 (Open Web Text)

Max Activating Token Index: 370

Text #12

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9261. Min Act: -0.1700

Data Index: 6474456 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9350. Min Act: -0.1700

Data Index: 4240260 (Open Web Text)

Max Activating Token Index: 734

Text #14

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9248. Min Act: -0.1700

Data Index: 1034779 (Open Web Text)

Max Activating Token Index: 596

Text #15

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.8677. Min Act: -0.1700

Data Index: 4595412 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9270. Min Act: -0.1700

Data Index: 1281708 (Open Web Text)

Max Activating Token Index: 391

Text #17

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9164. Min Act: -0.1700

Data Index: 3562162 (Open Web Text)

Max Activating Token Index: 997

Text #18

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.9292. Min Act: -0.1700

Data Index: 4463986 (Open Web Text)

Max Activating Token Index: 564

Text #19

Max Range: 4.2295. Min Range: -4.2295

Max Act: 3.8763. Min Act: -0.1700

Data Index: 4435124 (Open Web Text)

Max Activating Token Index: 677