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

Dataset: Open Web Text

Neuron 2448 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: 2.0803. Min Range: -2.0803

Max Act: 2.0803. Min Act: -0.1700

Data Index: 4738809 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.9517. Min Act: -0.1700

Data Index: 8187141 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.9440. Min Act: -0.1700

Data Index: 2287988 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.9224. Min Act: -0.1700

Data Index: 5161974 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.9093. Min Act: -0.1698

Data Index: 8745191 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8969. Min Act: -0.1699

Data Index: 6459016 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8844. Min Act: -0.1690

Data Index: 1129095 (Open Web Text)

Max Activating Token Index: 43

Text #7

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8826. Min Act: -0.1699

Data Index: 6983163 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8709. Min Act: -0.1700

Data Index: 2297717 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8713. Min Act: -0.1699

Data Index: 6104680 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8695. Min Act: -0.1661

Data Index: 477767 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8567. Min Act: -0.1700

Data Index: 8447850 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8567. Min Act: -0.1697

Data Index: 1843343 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8426. Min Act: -0.1697

Data Index: 6233839 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8482. Min Act: -0.1700

Data Index: 7600042 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8444. Min Act: -0.1684

Data Index: 2392496 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8416. Min Act: -0.1700

Data Index: 2861862 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8413. Min Act: -0.1700

Data Index: 3301867 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8445. Min Act: -0.1694

Data Index: 3382501 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 2.0803. Min Range: -2.0803

Max Act: 1.8434. Min Act: -0.1700

Data Index: 1429953 (Open Web Text)

Max Activating Token Index: 10