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

Dataset: Open Web Text

Neuron 2073 in Layer 1

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: 1.7893. Min Range: -1.7893

Max Act: 1.7834. Min Act: -0.1700

Data Index: 3273321 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.7893. Min Act: -0.1700

Data Index: 3898946 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.7365. Min Act: -0.1700

Data Index: 5800490 (Open Web Text)

Max Activating Token Index: 850

Text #3

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.7370. Min Act: -0.1700

Data Index: 6853525 (Open Web Text)

Max Activating Token Index: 812

Text #4

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.7202. Min Act: -0.1698

Data Index: 8706982 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.7030. Min Act: -0.1700

Data Index: 352911 (Open Web Text)

Max Activating Token Index: 72

Text #6

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.7110. Min Act: -0.1700

Data Index: 8700075 (Open Web Text)

Max Activating Token Index: 94

Text #7

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.7095. Min Act: -0.1699

Data Index: 5927816 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6872. Min Act: -0.1700

Data Index: 5175884 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6924. Min Act: -0.1700

Data Index: 8373911 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6793. Min Act: -0.1699

Data Index: 2979919 (Open Web Text)

Max Activating Token Index: 84

Text #11

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6693. Min Act: -0.1700

Data Index: 4859648 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6782. Min Act: -0.1700

Data Index: 3392466 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6657. Min Act: -0.1700

Data Index: 348291 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6679. Min Act: -0.1700

Data Index: 7451824 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6798. Min Act: -0.1700

Data Index: 4826637 (Open Web Text)

Max Activating Token Index: 369

Text #16

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6688. Min Act: -0.1700

Data Index: 6853527 (Open Web Text)

Max Activating Token Index: 507

Text #17

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6594. Min Act: -0.1700

Data Index: 6853529 (Open Web Text)

Max Activating Token Index: 75

Text #18

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6650. Min Act: -0.1700

Data Index: 2170118 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 1.7893. Min Range: -1.7893

Max Act: 1.6684. Min Act: -0.1699

Data Index: 6853526 (Open Web Text)

Max Activating Token Index: 79