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

Dataset: Open Web Text

Neuron 276 in Layer 2

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: 3.4477. Min Range: -3.4477

Max Act: 3.4477. Min Act: -0.1700

Data Index: 7804393 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3852. Min Act: -0.1700

Data Index: 3410269 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3713. Min Act: -0.1700

Data Index: 3365586 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1782412 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3627. Min Act: -0.1700

Data Index: 7879605 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3527. Min Act: -0.1700

Data Index: 1697176 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2892. Min Act: -0.1700

Data Index: 5259921 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2918. Min Act: -0.1700

Data Index: 6864502 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2723. Min Act: -0.1700

Data Index: 2235817 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2620. Min Act: -0.1700

Data Index: 250982 (Open Web Text)

Max Activating Token Index: 976

Text #10

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2385. Min Act: -0.1700

Data Index: 2680194 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2429. Min Act: -0.1700

Data Index: 3789818 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2364. Min Act: -0.1700

Data Index: 230844 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.1918. Min Act: -0.1700

Data Index: 2857062 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.1904. Min Act: -0.1700

Data Index: 5955462 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.1952. Min Act: -0.1700

Data Index: 5708001 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.1807. Min Act: -0.1700

Data Index: 5314856 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.1856. Min Act: -0.1700

Data Index: 6672577 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.1881. Min Act: -0.1700

Data Index: 4254048 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.1923. Min Act: -0.1700

Data Index: 3723641 (Open Web Text)

Max Activating Token Index: 1023