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

Dataset: Open Web Text

Neuron 1899 in Layer 5

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: 4.1075. Min Range: -4.1075

Max Act: 4.1075. Min Act: -0.1700

Data Index: 6916843 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 4.1075. Min Range: -4.1075

Max Act: 4.0629. Min Act: -0.1700

Data Index: 2027457 (Open Web Text)

Max Activating Token Index: 904

Text #2

Max Range: 4.1075. Min Range: -4.1075

Max Act: 4.0267. Min Act: -0.1700

Data Index: 6982847 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 4.1075. Min Range: -4.1075

Max Act: 4.0119. Min Act: -0.1700

Data Index: 6281264 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9499. Min Act: -0.1700

Data Index: 1871496 (Open Web Text)

Max Activating Token Index: 747

Text #5

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9418. Min Act: -0.1700

Data Index: 6582177 (Open Web Text)

Max Activating Token Index: 552

Text #6

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9658. Min Act: -0.1700

Data Index: 8591901 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9813. Min Act: -0.1700

Data Index: 8353992 (Open Web Text)

Max Activating Token Index: 189

Text #8

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9520. Min Act: -0.1700

Data Index: 198046 (Open Web Text)

Max Activating Token Index: 631

Text #9

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9642. Min Act: -0.1700

Data Index: 913905 (Open Web Text)

Max Activating Token Index: 766

Text #10

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9431. Min Act: -0.1700

Data Index: 7623946 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9434. Min Act: -0.1700

Data Index: 333076 (Open Web Text)

Max Activating Token Index: 247

Text #12

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9337. Min Act: -0.1700

Data Index: 5353610 (Open Web Text)

Max Activating Token Index: 549

Text #13

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9268. Min Act: -0.1700

Data Index: 634443 (Open Web Text)

Max Activating Token Index: 197

Text #14

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9215. Min Act: -0.1700

Data Index: 5043591 (Open Web Text)

Max Activating Token Index: 82

Text #15

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9780. Min Act: -0.1700

Data Index: 5757349 (Open Web Text)

Max Activating Token Index: 991

Text #16

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9433. Min Act: -0.1700

Data Index: 3216004 (Open Web Text)

Max Activating Token Index: 728

Text #17

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9097. Min Act: -0.1700

Data Index: 5699702 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.9346. Min Act: -0.1700

Data Index: 6263728 (Open Web Text)

Max Activating Token Index: 159

Text #19

Max Range: 4.1075. Min Range: -4.1075

Max Act: 3.8821. Min Act: -0.1700

Data Index: 4676141 (Open Web Text)

Max Activating Token Index: 767