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

Dataset: Open Web Text

Neuron 1647 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: 3.9222. Min Range: -3.9222

Max Act: 3.9222. Min Act: -0.1700

Data Index: 248195 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.8832. Min Act: -0.1700

Data Index: 3259311 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.8504. Min Act: -0.1700

Data Index: 2317353 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.8553. Min Act: -0.1700

Data Index: 87734 (Open Web Text)

Max Activating Token Index: 90

Text #4

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.8439. Min Act: -0.1700

Data Index: 1495975 (Open Web Text)

Max Activating Token Index: 777

Text #5

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7717. Min Act: -0.1700

Data Index: 1431205 (Open Web Text)

Max Activating Token Index: 703

Text #6

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.8010. Min Act: -0.1700

Data Index: 5472280 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7567. Min Act: -0.1700

Data Index: 6579998 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7990. Min Act: -0.1700

Data Index: 3868019 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1645940 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7210. Min Act: -0.1700

Data Index: 6737480 (Open Web Text)

Max Activating Token Index: 715

Text #11

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7048. Min Act: -0.1700

Data Index: 4562205 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7026. Min Act: -0.1700

Data Index: 8407788 (Open Web Text)

Max Activating Token Index: 699

Text #13

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.6740. Min Act: -0.1700

Data Index: 1904168 (Open Web Text)

Max Activating Token Index: 337

Text #14

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.6774. Min Act: -0.1700

Data Index: 875808 (Open Web Text)

Max Activating Token Index: 417

Text #15

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.7101. Min Act: -0.1700

Data Index: 3388120 (Open Web Text)

Max Activating Token Index: 45

Text #16

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.6795. Min Act: -0.1700

Data Index: 5616180 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.6256. Min Act: -0.1700

Data Index: 256269 (Open Web Text)

Max Activating Token Index: 714

Text #18

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.6331. Min Act: -0.1700

Data Index: 1735514 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 3.9222. Min Range: -3.9222

Max Act: 3.6397. Min Act: -0.1700

Data Index: 6671609 (Open Web Text)

Max Activating Token Index: 51