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

Dataset: Open Web Text

Neuron 3047 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: 4.2860. Min Range: -4.2860

Max Act: 4.2860. Min Act: -0.1700

Data Index: 4099657 (Open Web Text)

Max Activating Token Index: 970

Text #1

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.2308. Min Act: -0.1700

Data Index: 3581398 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1926. Min Act: -0.1700

Data Index: 5292851 (Open Web Text)

Max Activating Token Index: 341

Text #3

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1684. Min Act: -0.1700

Data Index: 3172282 (Open Web Text)

Max Activating Token Index: 943

Text #4

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1930. Min Act: -0.1700

Data Index: 4102537 (Open Web Text)

Max Activating Token Index: 855

Text #5

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1539. Min Act: -0.1700

Data Index: 734982 (Open Web Text)

Max Activating Token Index: 660

Text #6

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1358. Min Act: -0.1700

Data Index: 139612 (Open Web Text)

Max Activating Token Index: 986

Text #7

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1117. Min Act: -0.1700

Data Index: 3741491 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1117. Min Act: -0.1700

Data Index: 7689542 (Open Web Text)

Max Activating Token Index: 382

Text #9

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1060. Min Act: -0.1700

Data Index: 1877804 (Open Web Text)

Max Activating Token Index: 722

Text #10

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1166. Min Act: -0.1700

Data Index: 2528949 (Open Web Text)

Max Activating Token Index: 836

Text #11

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0797. Min Act: -0.1700

Data Index: 6042028 (Open Web Text)

Max Activating Token Index: 199

Text #12

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.1119. Min Act: -0.1700

Data Index: 7788149 (Open Web Text)

Max Activating Token Index: 470

Text #13

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0818. Min Act: -0.1700

Data Index: 247467 (Open Web Text)

Max Activating Token Index: 242

Text #14

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0955. Min Act: -0.1700

Data Index: 7515578 (Open Web Text)

Max Activating Token Index: 601

Text #15

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0843. Min Act: -0.1700

Data Index: 7435671 (Open Web Text)

Max Activating Token Index: 290

Text #16

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0771. Min Act: -0.1700

Data Index: 1117380 (Open Web Text)

Max Activating Token Index: 772

Text #17

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0897. Min Act: -0.1700

Data Index: 7234202 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0417. Min Act: -0.1700

Data Index: 6780906 (Open Web Text)

Max Activating Token Index: 680

Text #19

Max Range: 4.2860. Min Range: -4.2860

Max Act: 4.0426. Min Act: -0.1700

Data Index: 2121161 (Open Web Text)

Max Activating Token Index: 307