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

Dataset: Open Web Text

Neuron 204 in Layer 0

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: 1.2490. Min Range: -1.2490

Max Act: 1.2490. Min Act: -0.1700

Data Index: 426474 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.2475. Min Act: -0.1700

Data Index: 2954884 (Open Web Text)

Max Activating Token Index: 936

Text #2

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.2145. Min Act: -0.1700

Data Index: 7360440 (Open Web Text)

Max Activating Token Index: 931

Text #3

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.2151. Min Act: -0.1700

Data Index: 2292993 (Open Web Text)

Max Activating Token Index: 967

Text #4

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.2226. Min Act: -0.1700

Data Index: 4940560 (Open Web Text)

Max Activating Token Index: 923

Text #5

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.2026. Min Act: -0.1700

Data Index: 8824924 (Open Web Text)

Max Activating Token Index: 945

Text #6

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.2062. Min Act: -0.1700

Data Index: 2005381 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1966. Min Act: -0.1700

Data Index: 1829509 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1871. Min Act: -0.1700

Data Index: 5025458 (Open Web Text)

Max Activating Token Index: 885

Text #9

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1784. Min Act: -0.1700

Data Index: 8718303 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1855. Min Act: -0.1700

Data Index: 8060265 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1830. Min Act: -0.1700

Data Index: 6028505 (Open Web Text)

Max Activating Token Index: 936

Text #12

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1887. Min Act: -0.1700

Data Index: 1633773 (Open Web Text)

Max Activating Token Index: 950

Text #13

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1873. Min Act: -0.1700

Data Index: 3887165 (Open Web Text)

Max Activating Token Index: 945

Text #14

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1758. Min Act: -0.1700

Data Index: 2270370 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1738. Min Act: -0.1700

Data Index: 3956498 (Open Web Text)

Max Activating Token Index: 923

Text #16

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1792. Min Act: -0.1700

Data Index: 4481325 (Open Web Text)

Max Activating Token Index: 964

Text #17

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1709. Min Act: -0.1700

Data Index: 1005366 (Open Web Text)

Max Activating Token Index: 933

Text #18

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1833. Min Act: -0.1700

Data Index: 2753531 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 1.2490. Min Range: -1.2490

Max Act: 1.1722. Min Act: -0.1700

Data Index: 4559877 (Open Web Text)

Max Activating Token Index: 920