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

Dataset: Open Web Text

Neuron 1624 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: 2.3675. Min Range: -2.3675

Max Act: 2.3413. Min Act: -0.1700

Data Index: 96900 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.3675. Min Act: -0.1700

Data Index: 1030391 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.3043. Min Act: -0.1700

Data Index: 870586 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.3379. Min Act: -0.1700

Data Index: 1502465 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.3265. Min Act: -0.1700

Data Index: 7198615 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.3230. Min Act: -0.1700

Data Index: 8387630 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.3187. Min Act: -0.1700

Data Index: 564253 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.2532. Min Act: -0.1700

Data Index: 4747589 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.2176. Min Act: -0.1700

Data Index: 2838998 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.2320. Min Act: -0.1700

Data Index: 2985769 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.2256. Min Act: -0.1700

Data Index: 6897054 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.1896. Min Act: -0.1700

Data Index: 901227 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.1734. Min Act: -0.1700

Data Index: 4326496 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.2287. Min Act: -0.1700

Data Index: 5239428 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.1986. Min Act: -0.1700

Data Index: 7163161 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.1824. Min Act: -0.1700

Data Index: 1441431 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.1855. Min Act: -0.1700

Data Index: 2875886 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.1587. Min Act: -0.1700

Data Index: 4398783 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.1833. Min Act: -0.1700

Data Index: 2221724 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.3675. Min Range: -2.3675

Max Act: 2.1845. Min Act: -0.1700

Data Index: 8116906 (Open Web Text)

Max Activating Token Index: 1023