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

Dataset: Open Web Text

Neuron 2802 in Layer 4

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: 5.8165. Min Range: -5.8165

Max Act: 5.8056. Min Act: -0.1700

Data Index: 4305944 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.8165. Min Act: -0.1700

Data Index: 5883722 (Open Web Text)

Max Activating Token Index: 817

Text #2

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.6738. Min Act: -0.1700

Data Index: 1780837 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.5036. Min Act: -0.1700

Data Index: 4187138 (Open Web Text)

Max Activating Token Index: 878

Text #4

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.4867. Min Act: -0.1700

Data Index: 4887817 (Open Web Text)

Max Activating Token Index: 84

Text #5

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.4793. Min Act: -0.1700

Data Index: 5679775 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.4474. Min Act: -0.1700

Data Index: 4422840 (Open Web Text)

Max Activating Token Index: 396

Text #7

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.3784. Min Act: -0.1700

Data Index: 2241027 (Open Web Text)

Max Activating Token Index: 449

Text #8

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.3236. Min Act: -0.1700

Data Index: 1744214 (Open Web Text)

Max Activating Token Index: 596

Text #9

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.2237. Min Act: -0.1700

Data Index: 5211015 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.1892. Min Act: -0.1700

Data Index: 5074854 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.1761. Min Act: -0.1700

Data Index: 7471801 (Open Web Text)

Max Activating Token Index: 681

Text #12

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.1055. Min Act: -0.1700

Data Index: 6229165 (Open Web Text)

Max Activating Token Index: 87

Text #13

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.1216. Min Act: -0.1700

Data Index: 7185434 (Open Web Text)

Max Activating Token Index: 950

Text #14

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.0486. Min Act: -0.1700

Data Index: 8650873 (Open Web Text)

Max Activating Token Index: 655

Text #15

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.0830. Min Act: -0.1700

Data Index: 299293 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.1081. Min Act: -0.1700

Data Index: 6153897 (Open Web Text)

Max Activating Token Index: 865

Text #17

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.0233. Min Act: -0.1700

Data Index: 7018338 (Open Web Text)

Max Activating Token Index: 169

Text #18

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.0724. Min Act: -0.1700

Data Index: 1728331 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 5.8165. Min Range: -5.8165

Max Act: 5.0734. Min Act: -0.1700

Data Index: 3325544 (Open Web Text)

Max Activating Token Index: 8