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

Dataset: Open Web Text

Neuron 173 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: 3.5676. Min Range: -3.5676

Max Act: 3.5589. Min Act: -0.1700

Data Index: 1327105 (Open Web Text)

Max Activating Token Index: 168

Text #1

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.5676. Min Act: -0.1700

Data Index: 8603038 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.5283. Min Act: -0.1700

Data Index: 3278115 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4976. Min Act: -0.1700

Data Index: 8506849 (Open Web Text)

Max Activating Token Index: 697

Text #4

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4891. Min Act: -0.1700

Data Index: 3915858 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4477. Min Act: -0.1700

Data Index: 3004795 (Open Web Text)

Max Activating Token Index: 85

Text #6

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4378. Min Act: -0.1700

Data Index: 8177979 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4539. Min Act: -0.1700

Data Index: 3763672 (Open Web Text)

Max Activating Token Index: 850

Text #8

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4709. Min Act: -0.1700

Data Index: 7376323 (Open Web Text)

Max Activating Token Index: 468

Text #9

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4438. Min Act: -0.1700

Data Index: 7939979 (Open Web Text)

Max Activating Token Index: 667

Text #10

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4309. Min Act: -0.1700

Data Index: 8778270 (Open Web Text)

Max Activating Token Index: 459

Text #11

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.3714. Min Act: -0.1700

Data Index: 3088988 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4178. Min Act: -0.1700

Data Index: 977087 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.4189. Min Act: -0.1700

Data Index: 3986816 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.3949. Min Act: -0.1700

Data Index: 7896891 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.3977. Min Act: -0.1700

Data Index: 7441619 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.3872. Min Act: -0.1700

Data Index: 7793256 (Open Web Text)

Max Activating Token Index: 260

Text #17

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.3936. Min Act: -0.1700

Data Index: 6227570 (Open Web Text)

Max Activating Token Index: 593

Text #18

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.3876. Min Act: -0.1700

Data Index: 1112767 (Open Web Text)

Max Activating Token Index: 576

Text #19

Max Range: 3.5676. Min Range: -3.5676

Max Act: 3.3981. Min Act: -0.1700

Data Index: 7491836 (Open Web Text)

Max Activating Token Index: 906