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

Dataset: Open Web Text

Neuron 1678 in Layer 6

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: 4.7022. Min Range: -4.7022

Max Act: 4.7022. Min Act: -0.1700

Data Index: 7303919 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.5914. Min Act: -0.1700

Data Index: 1472424 (Open Web Text)

Max Activating Token Index: 642

Text #2

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.5748. Min Act: -0.1700

Data Index: 3352549 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.5660. Min Act: -0.1700

Data Index: 5070098 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.5444. Min Act: -0.1700

Data Index: 6708871 (Open Web Text)

Max Activating Token Index: 564

Text #5

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.4952. Min Act: -0.1700

Data Index: 7263152 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.4846. Min Act: -0.1700

Data Index: 3379778 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.4657. Min Act: -0.1700

Data Index: 1864781 (Open Web Text)

Max Activating Token Index: 907

Text #8

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.4598. Min Act: -0.1700

Data Index: 6811812 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.4476. Min Act: -0.1700

Data Index: 6003157 (Open Web Text)

Max Activating Token Index: 322

Text #10

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.4304. Min Act: -0.1700

Data Index: 7502000 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.4116. Min Act: -0.1700

Data Index: 5130741 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.4168. Min Act: -0.1700

Data Index: 3257152 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.3538. Min Act: -0.1700

Data Index: 4496422 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.3794. Min Act: -0.1700

Data Index: 2540625 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.3633. Min Act: -0.1700

Data Index: 3188115 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.3626. Min Act: -0.1700

Data Index: 6377075 (Open Web Text)

Max Activating Token Index: 535

Text #17

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.3590. Min Act: -0.1700

Data Index: 2000979 (Open Web Text)

Max Activating Token Index: 217

Text #18

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.3951. Min Act: -0.1700

Data Index: 1556107 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 4.7022. Min Range: -4.7022

Max Act: 4.3759. Min Act: -0.1700

Data Index: 5379921 (Open Web Text)

Max Activating Token Index: 997