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

Dataset: Open Web Text

Neuron 469 in Layer 5

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: 4.2910. Min Range: -4.2910

Max Act: 4.2910. Min Act: -0.1700

Data Index: 2149300 (Open Web Text)

Max Activating Token Index: 314

Text #1

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2886. Min Act: -0.1700

Data Index: 7607768 (Open Web Text)

Max Activating Token Index: 182

Text #2

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2400. Min Act: -0.1700

Data Index: 2310968 (Open Web Text)

Max Activating Token Index: 833

Text #3

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2370. Min Act: -0.1700

Data Index: 3613777 (Open Web Text)

Max Activating Token Index: 565

Text #4

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2558. Min Act: -0.1700

Data Index: 4970107 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2388. Min Act: -0.1700

Data Index: 8269642 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2280. Min Act: -0.1700

Data Index: 1790919 (Open Web Text)

Max Activating Token Index: 426

Text #7

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2224. Min Act: -0.1700

Data Index: 5430085 (Open Web Text)

Max Activating Token Index: 769

Text #8

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2045. Min Act: -0.1700

Data Index: 4373065 (Open Web Text)

Max Activating Token Index: 877

Text #9

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2046. Min Act: -0.1700

Data Index: 6386865 (Open Web Text)

Max Activating Token Index: 460

Text #10

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1948. Min Act: -0.1700

Data Index: 2323767 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1891. Min Act: -0.1700

Data Index: 5078199 (Open Web Text)

Max Activating Token Index: 858

Text #12

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1797. Min Act: -0.1700

Data Index: 5164705 (Open Web Text)

Max Activating Token Index: 791

Text #13

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1784. Min Act: -0.1700

Data Index: 1642098 (Open Web Text)

Max Activating Token Index: 853

Text #14

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1883. Min Act: -0.1700

Data Index: 3201105 (Open Web Text)

Max Activating Token Index: 571

Text #15

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1960. Min Act: -0.1700

Data Index: 963933 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.2007. Min Act: -0.1700

Data Index: 7523108 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1751. Min Act: -0.1700

Data Index: 2064847 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1416. Min Act: -0.1700

Data Index: 1366065 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 4.2910. Min Range: -4.2910

Max Act: 4.1775. Min Act: -0.1700

Data Index: 1751806 (Open Web Text)

Max Activating Token Index: 601