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

Dataset: Open Web Text

Neuron 1827 in Layer 1

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: 1.4196. Min Range: -1.4196

Max Act: 1.4087. Min Act: -0.1693

Data Index: 8260250 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.4196. Min Act: -0.1697

Data Index: 1880173 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.4017. Min Act: -0.1696

Data Index: 8684950 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3928. Min Act: -0.1698

Data Index: 6103351 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3996. Min Act: -0.1700

Data Index: 408033 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3910. Min Act: -0.1700

Data Index: 7492003 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3895. Min Act: -0.1700

Data Index: 8327811 (Open Web Text)

Max Activating Token Index: 626

Text #7

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3898. Min Act: -0.1699

Data Index: 4488985 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3884. Min Act: -0.1700

Data Index: 2007345 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3861. Min Act: -0.1700

Data Index: 6436523 (Open Web Text)

Max Activating Token Index: 193

Text #10

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3804. Min Act: -0.1700

Data Index: 6876197 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3806. Min Act: -0.1687

Data Index: 2170903 (Open Web Text)

Max Activating Token Index: 961

Text #12

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3696. Min Act: -0.1698

Data Index: 7824462 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3808. Min Act: -0.1700

Data Index: 7010456 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3723. Min Act: -0.1690

Data Index: 6777909 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3678. Min Act: -0.1700

Data Index: 2079242 (Open Web Text)

Max Activating Token Index: 916

Text #16

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3723. Min Act: -0.1700

Data Index: 1819899 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3633. Min Act: -0.1700

Data Index: 1824963 (Open Web Text)

Max Activating Token Index: 213

Text #18

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3669. Min Act: -0.1700

Data Index: 3084189 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 1.4196. Min Range: -1.4196

Max Act: 1.3629. Min Act: -0.1694

Data Index: 5111182 (Open Web Text)

Max Activating Token Index: 288