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

Dataset: Open Web Text

Neuron 2436 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: 3.1836. Min Range: -3.1836

Max Act: 3.1836. Min Act: -0.1700

Data Index: 5598277 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.9841. Min Act: -0.1700

Data Index: 2358102 (Open Web Text)

Max Activating Token Index: 917

Text #2

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.9792. Min Act: -0.1700

Data Index: 6641073 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.9734. Min Act: -0.1700

Data Index: 8257792 (Open Web Text)

Max Activating Token Index: 92

Text #4

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.9374. Min Act: -0.1700

Data Index: 8830765 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.9307. Min Act: -0.1700

Data Index: 7904350 (Open Web Text)

Max Activating Token Index: 709

Text #6

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8213. Min Act: -0.1700

Data Index: 5987651 (Open Web Text)

Max Activating Token Index: 244

Text #7

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8114. Min Act: -0.1700

Data Index: 4280135 (Open Web Text)

Max Activating Token Index: 622

Text #8

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8244. Min Act: -0.1700

Data Index: 4280134 (Open Web Text)

Max Activating Token Index: 761

Text #9

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8170. Min Act: -0.1700

Data Index: 8779632 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8149. Min Act: -0.1700

Data Index: 8446006 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8339. Min Act: -0.1700

Data Index: 1773083 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8062. Min Act: -0.1700

Data Index: 408245 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8212. Min Act: -0.1700

Data Index: 5421352 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8006. Min Act: -0.1700

Data Index: 1169687 (Open Web Text)

Max Activating Token Index: 669

Text #15

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.7881. Min Act: -0.1700

Data Index: 6734932 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8086. Min Act: -0.1700

Data Index: 901863 (Open Web Text)

Max Activating Token Index: 938

Text #17

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.8255. Min Act: -0.1700

Data Index: 5843486 (Open Web Text)

Max Activating Token Index: 964

Text #18

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.7990. Min Act: -0.1700

Data Index: 6596492 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 3.1836. Min Range: -3.1836

Max Act: 2.7298. Min Act: -0.1700

Data Index: 2072868 (Open Web Text)

Max Activating Token Index: 628