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

Dataset: Open Web Text

Neuron 1555 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: 5.0017. Min Range: -5.0017

Max Act: 5.0017. Min Act: -0.1700

Data Index: 801391 (Open Web Text)

Max Activating Token Index: 746

Text #1

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8990. Min Act: -0.1700

Data Index: 4666394 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8839. Min Act: -0.1700

Data Index: 164888 (Open Web Text)

Max Activating Token Index: 652

Text #3

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8820. Min Act: -0.1700

Data Index: 1401551 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8853. Min Act: -0.1700

Data Index: 7671904 (Open Web Text)

Max Activating Token Index: 756

Text #5

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8675. Min Act: -0.1700

Data Index: 5184406 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8772. Min Act: -0.1700

Data Index: 3945819 (Open Web Text)

Max Activating Token Index: 812

Text #7

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8107. Min Act: -0.1700

Data Index: 2802345 (Open Web Text)

Max Activating Token Index: 859

Text #8

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8326. Min Act: -0.1700

Data Index: 4433437 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8263. Min Act: -0.1700

Data Index: 2860614 (Open Web Text)

Max Activating Token Index: 622

Text #10

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8207. Min Act: -0.1700

Data Index: 289219 (Open Web Text)

Max Activating Token Index: 779

Text #11

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.7995. Min Act: -0.1700

Data Index: 4726147 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8160. Min Act: -0.1700

Data Index: 5381222 (Open Web Text)

Max Activating Token Index: 315

Text #13

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.7932. Min Act: -0.1700

Data Index: 3972053 (Open Web Text)

Max Activating Token Index: 455

Text #14

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.7863. Min Act: -0.1700

Data Index: 2043734 (Open Web Text)

Max Activating Token Index: 217

Text #15

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.7789. Min Act: -0.1700

Data Index: 749585 (Open Web Text)

Max Activating Token Index: 862

Text #16

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.7790. Min Act: -0.1700

Data Index: 7277163 (Open Web Text)

Max Activating Token Index: 977

Text #17

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.7636. Min Act: -0.1700

Data Index: 1800878 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.7802. Min Act: -0.1700

Data Index: 1900679 (Open Web Text)

Max Activating Token Index: 427

Text #19

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.7398. Min Act: -0.1700

Data Index: 2633531 (Open Web Text)

Max Activating Token Index: 446