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

Dataset: Open Web Text

Neuron 2919 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: 5.3614. Min Range: -5.3614

Max Act: 5.3540. Min Act: -0.1700

Data Index: 6794398 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.3614. Min Act: -0.1700

Data Index: 2488199 (Open Web Text)

Max Activating Token Index: 742

Text #2

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.3295. Min Act: -0.1700

Data Index: 8671988 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2987. Min Act: -0.1700

Data Index: 5309892 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2843. Min Act: -0.1700

Data Index: 6371754 (Open Web Text)

Max Activating Token Index: 826

Text #5

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2807. Min Act: -0.1700

Data Index: 5302297 (Open Web Text)

Max Activating Token Index: 490

Text #6

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2978. Min Act: -0.1700

Data Index: 5119739 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2901. Min Act: -0.1700

Data Index: 2131351 (Open Web Text)

Max Activating Token Index: 775

Text #8

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2253. Min Act: -0.1700

Data Index: 8239571 (Open Web Text)

Max Activating Token Index: 497

Text #9

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2164. Min Act: -0.1700

Data Index: 1684924 (Open Web Text)

Max Activating Token Index: 356

Text #10

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2359. Min Act: -0.1700

Data Index: 1642260 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2333. Min Act: -0.1700

Data Index: 1016659 (Open Web Text)

Max Activating Token Index: 724

Text #12

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2068. Min Act: -0.1700

Data Index: 1411054 (Open Web Text)

Max Activating Token Index: 474

Text #13

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2049. Min Act: -0.1700

Data Index: 724901 (Open Web Text)

Max Activating Token Index: 173

Text #14

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.1914. Min Act: -0.1700

Data Index: 2786746 (Open Web Text)

Max Activating Token Index: 504

Text #15

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2000. Min Act: -0.1700

Data Index: 7034501 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2066. Min Act: -0.1700

Data Index: 7205687 (Open Web Text)

Max Activating Token Index: 371

Text #17

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2023. Min Act: -0.1700

Data Index: 7874838 (Open Web Text)

Max Activating Token Index: 268

Text #18

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.2000. Min Act: -0.1700

Data Index: 5818896 (Open Web Text)

Max Activating Token Index: 571

Text #19

Max Range: 5.3614. Min Range: -5.3614

Max Act: 5.1984. Min Act: -0.1700

Data Index: 5432760 (Open Web Text)

Max Activating Token Index: 712