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

Dataset: Open Web Text

Neuron 2546 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: 4.0225. Min Range: -4.0225

Max Act: 4.0225. Min Act: -0.1700

Data Index: 7942197 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9732. Min Act: -0.1700

Data Index: 2432162 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9317. Min Act: -0.1700

Data Index: 1341946 (Open Web Text)

Max Activating Token Index: 972

Text #3

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9584. Min Act: -0.1700

Data Index: 8010875 (Open Web Text)

Max Activating Token Index: 953

Text #4

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9433. Min Act: -0.1700

Data Index: 5886969 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9151. Min Act: -0.1700

Data Index: 3375841 (Open Web Text)

Max Activating Token Index: 833

Text #6

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9186. Min Act: -0.1700

Data Index: 1915954 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9092. Min Act: -0.1700

Data Index: 498744 (Open Web Text)

Max Activating Token Index: 954

Text #8

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9167. Min Act: -0.1700

Data Index: 1012347 (Open Web Text)

Max Activating Token Index: 877

Text #9

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.9034. Min Act: -0.1700

Data Index: 4114086 (Open Web Text)

Max Activating Token Index: 293

Text #10

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8645. Min Act: -0.1700

Data Index: 6190613 (Open Web Text)

Max Activating Token Index: 836

Text #11

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8624. Min Act: -0.1700

Data Index: 3576971 (Open Web Text)

Max Activating Token Index: 732

Text #12

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8764. Min Act: -0.1700

Data Index: 5621416 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8779. Min Act: -0.1700

Data Index: 1552210 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8756. Min Act: -0.1700

Data Index: 7553625 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8668. Min Act: -0.1700

Data Index: 5080008 (Open Web Text)

Max Activating Token Index: 960

Text #16

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8820. Min Act: -0.1700

Data Index: 4872500 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8740. Min Act: -0.1700

Data Index: 4816357 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8687. Min Act: -0.1700

Data Index: 8705891 (Open Web Text)

Max Activating Token Index: 943

Text #19

Max Range: 4.0225. Min Range: -4.0225

Max Act: 3.8501. Min Act: -0.1700

Data Index: 2073350 (Open Web Text)

Max Activating Token Index: 329