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

Dataset: Open Web Text

Neuron 695 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: 8.4794. Min Range: -8.4794

Max Act: 8.4794. Min Act: -0.1700

Data Index: 4648097 (Open Web Text)

Max Activating Token Index: 285

Text #1

Max Range: 8.4794. Min Range: -8.4794

Max Act: 8.2949. Min Act: -0.1700

Data Index: 2560246 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.9447. Min Act: -0.1700

Data Index: 2141911 (Open Web Text)

Max Activating Token Index: 716

Text #3

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.6520. Min Act: -0.1653

Data Index: 5161072 (Open Web Text)

Max Activating Token Index: 692

Text #4

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.3964. Min Act: -0.1700

Data Index: 880300 (Open Web Text)

Max Activating Token Index: 117

Text #5

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.4499. Min Act: -0.1700

Data Index: 2794150 (Open Web Text)

Max Activating Token Index: 836

Text #6

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.3696. Min Act: -0.1700

Data Index: 1616803 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.1817. Min Act: -0.1700

Data Index: 5161071 (Open Web Text)

Max Activating Token Index: 860

Text #8

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.1581. Min Act: -0.1700

Data Index: 2141919 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.0451. Min Act: -0.1700

Data Index: 7123760 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 8.4794. Min Range: -8.4794

Max Act: 7.0425. Min Act: -0.1700

Data Index: 1137079 (Open Web Text)

Max Activating Token Index: 909

Text #11

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.9230. Min Act: -0.1700

Data Index: 2407858 (Open Web Text)

Max Activating Token Index: 795

Text #12

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.8501. Min Act: -0.1700

Data Index: 2407857 (Open Web Text)

Max Activating Token Index: 738

Text #13

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.8245. Min Act: -0.1700

Data Index: 5161073 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.7963. Min Act: -0.1700

Data Index: 2897232 (Open Web Text)

Max Activating Token Index: 213

Text #15

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.6869. Min Act: -0.1700

Data Index: 2407860 (Open Web Text)

Max Activating Token Index: 744

Text #16

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.6241. Min Act: -0.1700

Data Index: 4038964 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.7007. Min Act: -0.1700

Data Index: 2220549 (Open Web Text)

Max Activating Token Index: 90

Text #18

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.6637. Min Act: -0.1653

Data Index: 5770360 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 8.4794. Min Range: -8.4794

Max Act: 6.5527. Min Act: -0.1700

Data Index: 4256610 (Open Web Text)

Max Activating Token Index: 556