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

Dataset: Open Web Text

Neuron 1482 in Layer 4

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: 3.9331. Min Range: -3.9331

Max Act: 3.9331. Min Act: -0.1700

Data Index: 4783018 (Open Web Text)

Max Activating Token Index: 604

Text #1

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.8466. Min Act: -0.1700

Data Index: 4690178 (Open Web Text)

Max Activating Token Index: 473

Text #2

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7832. Min Act: -0.1700

Data Index: 3661864 (Open Web Text)

Max Activating Token Index: 921

Text #3

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7990. Min Act: -0.1700

Data Index: 6245796 (Open Web Text)

Max Activating Token Index: 950

Text #4

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7655. Min Act: -0.1700

Data Index: 5780498 (Open Web Text)

Max Activating Token Index: 213

Text #5

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7321. Min Act: -0.1700

Data Index: 1123889 (Open Web Text)

Max Activating Token Index: 791

Text #6

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7261. Min Act: -0.1700

Data Index: 3030110 (Open Web Text)

Max Activating Token Index: 442

Text #7

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7389. Min Act: -0.1700

Data Index: 2555863 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7047. Min Act: -0.1700

Data Index: 15434 (Open Web Text)

Max Activating Token Index: 462

Text #9

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7251. Min Act: -0.1700

Data Index: 1852617 (Open Web Text)

Max Activating Token Index: 124

Text #10

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6995. Min Act: -0.1700

Data Index: 7714905 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6913. Min Act: -0.1700

Data Index: 294934 (Open Web Text)

Max Activating Token Index: 491

Text #12

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7136. Min Act: -0.1700

Data Index: 6084219 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6799. Min Act: -0.1700

Data Index: 2165277 (Open Web Text)

Max Activating Token Index: 218

Text #14

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.7116. Min Act: -0.1700

Data Index: 6420301 (Open Web Text)

Max Activating Token Index: 515

Text #15

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6625. Min Act: -0.1700

Data Index: 4269419 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6473. Min Act: -0.1700

Data Index: 3314331 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6562. Min Act: -0.1700

Data Index: 6068247 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6007. Min Act: -0.1700

Data Index: 298861 (Open Web Text)

Max Activating Token Index: 104

Text #19

Max Range: 3.9331. Min Range: -3.9331

Max Act: 3.6093. Min Act: -0.1700

Data Index: 4555181 (Open Web Text)

Max Activating Token Index: 744