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

Dataset: Open Web Text

Neuron 598 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: 2.7739. Min Range: -2.7739

Max Act: 2.7640. Min Act: -0.1700

Data Index: 2025579 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7739. Min Act: -0.1700

Data Index: 2032801 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7712. Min Act: -0.1700

Data Index: 5743134 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7701. Min Act: -0.1700

Data Index: 298156 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7640. Min Act: -0.1700

Data Index: 7896023 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7471. Min Act: -0.1700

Data Index: 5158965 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7321. Min Act: -0.1700

Data Index: 341739 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7193. Min Act: -0.1700

Data Index: 1935981 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7094. Min Act: -0.1700

Data Index: 5878779 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7211. Min Act: -0.1700

Data Index: 5004480 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.7165. Min Act: -0.1700

Data Index: 8456751 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6980. Min Act: -0.1700

Data Index: 3025141 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6976. Min Act: -0.1700

Data Index: 2135684 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6980. Min Act: -0.1700

Data Index: 1198221 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6976. Min Act: -0.1700

Data Index: 2734752 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6980. Min Act: -0.1700

Data Index: 6851201 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6976. Min Act: -0.1700

Data Index: 7454770 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6845. Min Act: -0.1700

Data Index: 3337496 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6897. Min Act: -0.1700

Data Index: 2554121 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 2.7739. Min Range: -2.7739

Max Act: 2.6649. Min Act: -0.1700

Data Index: 544918 (Open Web Text)

Max Activating Token Index: 96