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

Dataset: Open Web Text

Neuron 973 in Layer 3

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: 1.7072. Min Range: -1.7072

Max Act: 1.7072. Min Act: -0.1700

Data Index: 8741771 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.6075. Min Act: -0.1700

Data Index: 8213866 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5963. Min Act: -0.1700

Data Index: 4117945 (Open Web Text)

Max Activating Token Index: 461

Text #3

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5874. Min Act: -0.1700

Data Index: 2093903 (Open Web Text)

Max Activating Token Index: 873

Text #4

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5790. Min Act: -0.1700

Data Index: 3631421 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5780. Min Act: -0.1699

Data Index: 5125297 (Open Web Text)

Max Activating Token Index: 360

Text #6

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5542. Min Act: -0.1700

Data Index: 7185989 (Open Web Text)

Max Activating Token Index: 813

Text #7

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5432. Min Act: -0.1700

Data Index: 69318 (Open Web Text)

Max Activating Token Index: 678

Text #8

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5391. Min Act: -0.1700

Data Index: 1492414 (Open Web Text)

Max Activating Token Index: 910

Text #9

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5566. Min Act: -0.1700

Data Index: 6498139 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5477. Min Act: -0.1700

Data Index: 7502837 (Open Web Text)

Max Activating Token Index: 167

Text #11

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5419. Min Act: -0.1700

Data Index: 6317805 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5295. Min Act: -0.1700

Data Index: 8212344 (Open Web Text)

Max Activating Token Index: 871

Text #13

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5460. Min Act: -0.1700

Data Index: 8174110 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5322. Min Act: -0.1700

Data Index: 1448764 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5144. Min Act: -0.1699

Data Index: 262757 (Open Web Text)

Max Activating Token Index: 135

Text #16

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5173. Min Act: -0.1700

Data Index: 2213068 (Open Web Text)

Max Activating Token Index: 894

Text #17

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5301. Min Act: -0.1700

Data Index: 8261067 (Open Web Text)

Max Activating Token Index: 718

Text #18

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5239. Min Act: -0.1700

Data Index: 8115982 (Open Web Text)

Max Activating Token Index: 470

Text #19

Max Range: 1.7072. Min Range: -1.7072

Max Act: 1.5339. Min Act: -0.1699

Data Index: 6285781 (Open Web Text)

Max Activating Token Index: 247