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

Dataset: Open Web Text

Neuron 1242 in Layer 6

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: 3.2905. Min Range: -3.2905

Max Act: 3.2905. Min Act: -0.1700

Data Index: 2217290 (Open Web Text)

Max Activating Token Index: 424

Text #1

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.2282. Min Act: -0.1700

Data Index: 7472456 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.2275. Min Act: -0.1700

Data Index: 2217280 (Open Web Text)

Max Activating Token Index: 274

Text #3

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.2201. Min Act: -0.1700

Data Index: 3228110 (Open Web Text)

Max Activating Token Index: 165

Text #4

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1429. Min Act: -0.1700

Data Index: 2199410 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1639. Min Act: -0.1700

Data Index: 2654709 (Open Web Text)

Max Activating Token Index: 166

Text #6

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1988. Min Act: -0.1700

Data Index: 6877798 (Open Web Text)

Max Activating Token Index: 840

Text #7

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1798. Min Act: -0.1700

Data Index: 2217284 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1642. Min Act: -0.1700

Data Index: 472241 (Open Web Text)

Max Activating Token Index: 607

Text #9

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.2077. Min Act: -0.1700

Data Index: 4391584 (Open Web Text)

Max Activating Token Index: 914

Text #10

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1586. Min Act: -0.1700

Data Index: 8171592 (Open Web Text)

Max Activating Token Index: 809

Text #11

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1705. Min Act: -0.1700

Data Index: 1524814 (Open Web Text)

Max Activating Token Index: 47

Text #12

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1895. Min Act: -0.1700

Data Index: 2217291 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1535. Min Act: -0.1700

Data Index: 5559251 (Open Web Text)

Max Activating Token Index: 137

Text #14

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1405. Min Act: -0.1700

Data Index: 7066169 (Open Web Text)

Max Activating Token Index: 975

Text #15

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1459. Min Act: -0.1700

Data Index: 5216977 (Open Web Text)

Max Activating Token Index: 706

Text #16

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1343. Min Act: -0.1700

Data Index: 2217289 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1416. Min Act: -0.1700

Data Index: 3307674 (Open Web Text)

Max Activating Token Index: 148

Text #18

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1059. Min Act: -0.1700

Data Index: 2591022 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 3.2905. Min Range: -3.2905

Max Act: 3.1232. Min Act: -0.1700

Data Index: 472242 (Open Web Text)

Max Activating Token Index: 679