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

Dataset: Open Web Text

Neuron 2256 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: 4.9272. Min Range: -4.9272

Max Act: 4.9272. Min Act: -0.1700

Data Index: 8705789 (Open Web Text)

Max Activating Token Index: 558

Text #1

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.9215. Min Act: -0.1700

Data Index: 6341094 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7720. Min Act: -0.1700

Data Index: 5346466 (Open Web Text)

Max Activating Token Index: 700

Text #3

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7822. Min Act: -0.1700

Data Index: 4910273 (Open Web Text)

Max Activating Token Index: 436

Text #4

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7322. Min Act: -0.1700

Data Index: 3866815 (Open Web Text)

Max Activating Token Index: 938

Text #5

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7635. Min Act: -0.1700

Data Index: 5183435 (Open Web Text)

Max Activating Token Index: 596

Text #6

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6956. Min Act: -0.1700

Data Index: 1225326 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7040. Min Act: -0.1700

Data Index: 7169628 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.7145. Min Act: -0.1700

Data Index: 8005150 (Open Web Text)

Max Activating Token Index: 519

Text #9

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6919. Min Act: -0.1700

Data Index: 6360868 (Open Web Text)

Max Activating Token Index: 946

Text #10

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6258. Min Act: -0.1700

Data Index: 4583075 (Open Web Text)

Max Activating Token Index: 742

Text #11

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6906. Min Act: -0.1700

Data Index: 6650441 (Open Web Text)

Max Activating Token Index: 175

Text #12

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6571. Min Act: -0.1700

Data Index: 7650163 (Open Web Text)

Max Activating Token Index: 247

Text #13

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6802. Min Act: -0.1700

Data Index: 5345240 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6018. Min Act: -0.1700

Data Index: 8292680 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6546. Min Act: -0.1700

Data Index: 8603251 (Open Web Text)

Max Activating Token Index: 1006

Text #16

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6068. Min Act: -0.1700

Data Index: 8218936 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6216. Min Act: -0.1700

Data Index: 5681649 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.5828. Min Act: -0.1700

Data Index: 4992541 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 4.9272. Min Range: -4.9272

Max Act: 4.6120. Min Act: -0.1700

Data Index: 2421546 (Open Web Text)

Max Activating Token Index: 340