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

Dataset: Open Web Text

Neuron 641 in Layer 0

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: 4.6045. Min Range: -4.6045

Max Act: 4.6045. Min Act: -0.1700

Data Index: 4185147 (Open Web Text)

Max Activating Token Index: 710

Text #1

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.4826. Min Act: -0.1700

Data Index: 6944327 (Open Web Text)

Max Activating Token Index: 702

Text #2

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.4823. Min Act: -0.1073

Data Index: 426477 (Open Web Text)

Max Activating Token Index: 674

Text #3

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.4907. Min Act: -0.1700

Data Index: 1240182 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.4509. Min Act: -0.1700

Data Index: 3593372 (Open Web Text)

Max Activating Token Index: 61

Text #5

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.4321. Min Act: -0.1700

Data Index: 6869289 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.4228. Min Act: -0.1700

Data Index: 2550847 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3772. Min Act: -0.1676

Data Index: 3933771 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3796. Min Act: -0.1700

Data Index: 3458349 (Open Web Text)

Max Activating Token Index: 707

Text #9

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3722. Min Act: -0.1700

Data Index: 7729924 (Open Web Text)

Max Activating Token Index: 289

Text #10

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3617. Min Act: -0.1700

Data Index: 6100683 (Open Web Text)

Max Activating Token Index: 397

Text #11

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3591. Min Act: -0.1696

Data Index: 8164056 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3630. Min Act: -0.1689

Data Index: 6871922 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3540. Min Act: -0.1700

Data Index: 2214776 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3383. Min Act: -0.0721

Data Index: 5151632 (Open Web Text)

Max Activating Token Index: 29

Text #15

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3331. Min Act: -0.1700

Data Index: 2442404 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3519. Min Act: -0.1694

Data Index: 4631942 (Open Web Text)

Max Activating Token Index: 67

Text #17

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3342. Min Act: -0.1700

Data Index: 7685989 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3350. Min Act: -0.1676

Data Index: 4105063 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.6045. Min Range: -4.6045

Max Act: 4.3415. Min Act: -0.1700

Data Index: 1966405 (Open Web Text)

Max Activating Token Index: 845