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

Dataset: Open Web Text

Neuron 1397 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: 4.5719. Min Range: -4.5719

Max Act: 4.5719. Min Act: -0.1700

Data Index: 2385904 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.5079. Min Act: -0.1700

Data Index: 6797765 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.4801. Min Act: -0.1700

Data Index: 1463932 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.4133. Min Act: -0.1700

Data Index: 3086259 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3878. Min Act: -0.1700

Data Index: 2586903 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3930. Min Act: -0.1700

Data Index: 8244728 (Open Web Text)

Max Activating Token Index: 25

Text #6

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3940. Min Act: -0.1700

Data Index: 3001021 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3892. Min Act: -0.1700

Data Index: 7430673 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.4133. Min Act: -0.1700

Data Index: 3124764 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3781. Min Act: -0.1700

Data Index: 8199715 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3820. Min Act: -0.1700

Data Index: 8352519 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3389. Min Act: -0.1700

Data Index: 5923367 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3716. Min Act: -0.1700

Data Index: 7303874 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3301. Min Act: -0.1700

Data Index: 4772396 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3485. Min Act: -0.1700

Data Index: 6352511 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3716. Min Act: -0.1700

Data Index: 4837373 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3468. Min Act: -0.1700

Data Index: 3111929 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.2954. Min Act: -0.1700

Data Index: 300384 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3245. Min Act: -0.1700

Data Index: 791922 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.5719. Min Range: -4.5719

Max Act: 4.3159. Min Act: -0.1700

Data Index: 5299417 (Open Web Text)

Max Activating Token Index: 3