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

Dataset: Open Web Text

Neuron 2864 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: 4.2070. Min Range: -4.2070

Max Act: 4.2070. Min Act: -0.1700

Data Index: 1416914 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.1353. Min Act: -0.1700

Data Index: 2361875 (Open Web Text)

Max Activating Token Index: 557

Text #2

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0871. Min Act: -0.1700

Data Index: 4698430 (Open Web Text)

Max Activating Token Index: 731

Text #3

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0787. Min Act: -0.1700

Data Index: 4698425 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0504. Min Act: -0.1700

Data Index: 3480291 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0151. Min Act: -0.1700

Data Index: 266080 (Open Web Text)

Max Activating Token Index: 682

Text #6

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0039. Min Act: -0.1700

Data Index: 2648357 (Open Web Text)

Max Activating Token Index: 961

Text #7

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0168. Min Act: -0.1700

Data Index: 3675296 (Open Web Text)

Max Activating Token Index: 309

Text #8

Max Range: 4.2070. Min Range: -4.2070

Max Act: 4.0067. Min Act: -0.1700

Data Index: 7479755 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9933. Min Act: -0.1700

Data Index: 8108025 (Open Web Text)

Max Activating Token Index: 832

Text #10

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9862. Min Act: -0.1700

Data Index: 285061 (Open Web Text)

Max Activating Token Index: 899

Text #11

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9948. Min Act: -0.1700

Data Index: 4358512 (Open Web Text)

Max Activating Token Index: 723

Text #12

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9828. Min Act: -0.1700

Data Index: 8577171 (Open Web Text)

Max Activating Token Index: 813

Text #13

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9649. Min Act: -0.1700

Data Index: 2156351 (Open Web Text)

Max Activating Token Index: 914

Text #14

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9444. Min Act: -0.1700

Data Index: 5338053 (Open Web Text)

Max Activating Token Index: 725

Text #15

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9542. Min Act: -0.1700

Data Index: 6718179 (Open Web Text)

Max Activating Token Index: 420

Text #16

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9499. Min Act: -0.1700

Data Index: 900420 (Open Web Text)

Max Activating Token Index: 354

Text #17

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9201. Min Act: -0.1700

Data Index: 5905223 (Open Web Text)

Max Activating Token Index: 859

Text #18

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9683. Min Act: -0.1700

Data Index: 2777379 (Open Web Text)

Max Activating Token Index: 152

Text #19

Max Range: 4.2070. Min Range: -4.2070

Max Act: 3.9432. Min Act: -0.1700

Data Index: 3250329 (Open Web Text)

Max Activating Token Index: 933