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

Dataset: Open Web Text

Neuron 1011 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: 4.5025. Min Range: -4.5025

Max Act: 4.5025. Min Act: -0.1700

Data Index: 959006 (Open Web Text)

Max Activating Token Index: 937

Text #1

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3780. Min Act: -0.1700

Data Index: 6036302 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3718. Min Act: -0.1700

Data Index: 5546505 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3683. Min Act: -0.1700

Data Index: 7015976 (Open Web Text)

Max Activating Token Index: 714

Text #4

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.3731. Min Act: -0.1700

Data Index: 1413421 (Open Web Text)

Max Activating Token Index: 775

Text #5

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.2836. Min Act: -0.1700

Data Index: 6036301 (Open Web Text)

Max Activating Token Index: 496

Text #6

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.2699. Min Act: -0.1700

Data Index: 1413419 (Open Web Text)

Max Activating Token Index: 866

Text #7

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1640. Min Act: -0.1700

Data Index: 2225022 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1373. Min Act: -0.1700

Data Index: 6845748 (Open Web Text)

Max Activating Token Index: 491

Text #9

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1400. Min Act: -0.1700

Data Index: 429496 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1398. Min Act: -0.1700

Data Index: 324861 (Open Web Text)

Max Activating Token Index: 474

Text #11

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1428. Min Act: -0.1700

Data Index: 324862 (Open Web Text)

Max Activating Token Index: 523

Text #12

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1425. Min Act: -0.1700

Data Index: 2362793 (Open Web Text)

Max Activating Token Index: 600

Text #13

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1443. Min Act: -0.1700

Data Index: 959007 (Open Web Text)

Max Activating Token Index: 517

Text #14

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1286. Min Act: -0.1700

Data Index: 3251085 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1291. Min Act: -0.1700

Data Index: 4997897 (Open Web Text)

Max Activating Token Index: 929

Text #16

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1425. Min Act: -0.1700

Data Index: 1850402 (Open Web Text)

Max Activating Token Index: 156

Text #17

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1141. Min Act: -0.1700

Data Index: 5546506 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.1002. Min Act: -0.1700

Data Index: 6241488 (Open Web Text)

Max Activating Token Index: 840

Text #19

Max Range: 4.5025. Min Range: -4.5025

Max Act: 4.0620. Min Act: -0.1700

Data Index: 1413420 (Open Web Text)

Max Activating Token Index: 812