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

Dataset: Open Web Text

Neuron 1425 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: 4.7179. Min Range: -4.7179

Max Act: 4.7013. Min Act: -0.1700

Data Index: 365174 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.7179. Min Act: -0.1700

Data Index: 3702899 (Open Web Text)

Max Activating Token Index: 698

Text #2

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6939. Min Act: -0.1700

Data Index: 3561383 (Open Web Text)

Max Activating Token Index: 664

Text #3

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6907. Min Act: -0.1700

Data Index: 1438378 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6247. Min Act: -0.1700

Data Index: 3514301 (Open Web Text)

Max Activating Token Index: 156

Text #5

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6344. Min Act: -0.1700

Data Index: 8676091 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6494. Min Act: -0.1700

Data Index: 6054660 (Open Web Text)

Max Activating Token Index: 960

Text #7

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6104. Min Act: -0.1700

Data Index: 3495926 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6105. Min Act: -0.1700

Data Index: 725318 (Open Web Text)

Max Activating Token Index: 992

Text #9

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6370. Min Act: -0.1700

Data Index: 8813187 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6014. Min Act: -0.1700

Data Index: 2167914 (Open Web Text)

Max Activating Token Index: 851

Text #11

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6114. Min Act: -0.1700

Data Index: 3795028 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6187. Min Act: -0.1700

Data Index: 409028 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.6375. Min Act: -0.1700

Data Index: 6133739 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.5966. Min Act: -0.1700

Data Index: 6927473 (Open Web Text)

Max Activating Token Index: 679

Text #15

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.5840. Min Act: -0.1700

Data Index: 8604635 (Open Web Text)

Max Activating Token Index: 543

Text #16

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.5681. Min Act: -0.1700

Data Index: 6716303 (Open Web Text)

Max Activating Token Index: 958

Text #17

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.5696. Min Act: -0.1700

Data Index: 1074710 (Open Web Text)

Max Activating Token Index: 1014

Text #18

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.5393. Min Act: -0.1700

Data Index: 4303431 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 4.7179. Min Range: -4.7179

Max Act: 4.5497. Min Act: -0.1700

Data Index: 2845856 (Open Web Text)

Max Activating Token Index: 965