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

Dataset: Open Web Text

Neuron 3045 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: 4.2031. Min Range: -4.2031

Max Act: 4.1842. Min Act: -0.1700

Data Index: 847615 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.2031. Min Act: -0.1700

Data Index: 4242743 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1818. Min Act: -0.1700

Data Index: 5494249 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1753. Min Act: -0.1700

Data Index: 5085500 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1504. Min Act: -0.1700

Data Index: 1131560 (Open Web Text)

Max Activating Token Index: 877

Text #5

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1760. Min Act: -0.1700

Data Index: 5231921 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1571. Min Act: -0.1700

Data Index: 817961 (Open Web Text)

Max Activating Token Index: 530

Text #7

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1271. Min Act: -0.1700

Data Index: 5478431 (Open Web Text)

Max Activating Token Index: 912

Text #8

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1345. Min Act: -0.1700

Data Index: 6870944 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1644. Min Act: -0.1700

Data Index: 498176 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.1381. Min Act: -0.1700

Data Index: 804259 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 4.2031. Min Range: -4.2031

Max Act: 4.0584. Min Act: -0.1700

Data Index: 1579359 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.8412. Min Act: -0.1700

Data Index: 1579357 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.8464. Min Act: -0.1700

Data Index: 847613 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.8093. Min Act: -0.1700

Data Index: 5231919 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.7971. Min Act: -0.1700

Data Index: 5085498 (Open Web Text)

Max Activating Token Index: 592

Text #16

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.7883. Min Act: -0.1700

Data Index: 5494247 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.7994. Min Act: -0.1700

Data Index: 6870942 (Open Web Text)

Max Activating Token Index: 777

Text #18

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.7511. Min Act: -0.1700

Data Index: 4242741 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 4.2031. Min Range: -4.2031

Max Act: 3.7454. Min Act: -0.1700

Data Index: 498174 (Open Web Text)

Max Activating Token Index: 847