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

Dataset: Open Web Text

Neuron 2815 in Layer 0

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: 1.9193. Min Range: -1.9193

Max Act: 1.9193. Min Act: -0.1698

Data Index: 8720029 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.9083. Min Act: -0.1700

Data Index: 290886 (Open Web Text)

Max Activating Token Index: 813

Text #2

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8995. Min Act: -0.1700

Data Index: 4564233 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8902. Min Act: -0.1700

Data Index: 1412180 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8991. Min Act: -0.1700

Data Index: 7982259 (Open Web Text)

Max Activating Token Index: 209

Text #5

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8872. Min Act: -0.1700

Data Index: 8376441 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8888. Min Act: -0.1700

Data Index: 1326580 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8852. Min Act: -0.1700

Data Index: 4862102 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8757. Min Act: -0.1678

Data Index: 1110241 (Open Web Text)

Max Activating Token Index: 407

Text #9

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8748. Min Act: -0.1697

Data Index: 509007 (Open Web Text)

Max Activating Token Index: 368

Text #10

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8756. Min Act: -0.1700

Data Index: 3545196 (Open Web Text)

Max Activating Token Index: 77

Text #11

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8664. Min Act: -0.1700

Data Index: 3264265 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8640. Min Act: -0.1700

Data Index: 8077300 (Open Web Text)

Max Activating Token Index: 171

Text #13

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8664. Min Act: -0.1700

Data Index: 3815058 (Open Web Text)

Max Activating Token Index: 253

Text #14

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8643. Min Act: -0.1696

Data Index: 538757 (Open Web Text)

Max Activating Token Index: 283

Text #15

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8586. Min Act: -0.1699

Data Index: 1834201 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8633. Min Act: -0.1700

Data Index: 4066559 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8627. Min Act: -0.1700

Data Index: 4779458 (Open Web Text)

Max Activating Token Index: 110

Text #18

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8649. Min Act: -0.1700

Data Index: 307570 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 1.9193. Min Range: -1.9193

Max Act: 1.8511. Min Act: -0.1692

Data Index: 6486679 (Open Web Text)

Max Activating Token Index: 86