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

Dataset: Open Web Text

Neuron 1145 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: 2.6826. Min Range: -2.6826

Max Act: 2.6588. Min Act: -0.1700

Data Index: 696981 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.6826. Min Act: -0.1700

Data Index: 3647711 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.6092. Min Act: -0.1700

Data Index: 3569689 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.6148. Min Act: -0.1700

Data Index: 6352513 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.6015. Min Act: -0.1700

Data Index: 1316107 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.5470. Min Act: -0.1700

Data Index: 5333161 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.5065. Min Act: -0.1700

Data Index: 7325973 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.5116. Min Act: -0.1700

Data Index: 4512706 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4988. Min Act: -0.1700

Data Index: 4481511 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4906. Min Act: -0.1700

Data Index: 3152977 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4724. Min Act: -0.1700

Data Index: 3241010 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4471. Min Act: -0.1700

Data Index: 123913 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4572. Min Act: -0.1700

Data Index: 8219329 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4804. Min Act: -0.1700

Data Index: 2077430 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4353. Min Act: -0.1700

Data Index: 2108413 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4531. Min Act: -0.1700

Data Index: 3689344 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4543. Min Act: -0.1700

Data Index: 7682903 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4687. Min Act: -0.1700

Data Index: 5597407 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4517. Min Act: -0.1700

Data Index: 4594846 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.6826. Min Range: -2.6826

Max Act: 2.4346. Min Act: -0.1700

Data Index: 2561152 (Open Web Text)

Max Activating Token Index: 1023