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

Dataset: Open Web Text

Neuron 812 in Layer 3

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: 2.8245. Min Range: -2.8245

Max Act: 2.8245. Min Act: -0.1700

Data Index: 4416630 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.7482. Min Act: -0.1700

Data Index: 263330 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.7226. Min Act: -0.1700

Data Index: 6374872 (Open Web Text)

Max Activating Token Index: 396

Text #3

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.7545. Min Act: -0.1700

Data Index: 7955110 (Open Web Text)

Max Activating Token Index: 173

Text #4

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.7391. Min Act: -0.1700

Data Index: 5440602 (Open Web Text)

Max Activating Token Index: 803

Text #5

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.7084. Min Act: -0.1700

Data Index: 7630816 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.7103. Min Act: -0.1700

Data Index: 4776405 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.7068. Min Act: -0.1700

Data Index: 6827744 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.7073. Min Act: -0.1700

Data Index: 4494861 (Open Web Text)

Max Activating Token Index: 416

Text #9

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6939. Min Act: -0.1700

Data Index: 3599046 (Open Web Text)

Max Activating Token Index: 463

Text #10

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6778. Min Act: -0.1700

Data Index: 8757764 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6838. Min Act: -0.1700

Data Index: 8668797 (Open Web Text)

Max Activating Token Index: 756

Text #12

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6915. Min Act: -0.1700

Data Index: 2391478 (Open Web Text)

Max Activating Token Index: 349

Text #13

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6638. Min Act: -0.1700

Data Index: 4024763 (Open Web Text)

Max Activating Token Index: 240

Text #14

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6679. Min Act: -0.1700

Data Index: 3017749 (Open Web Text)

Max Activating Token Index: 330

Text #15

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6622. Min Act: -0.1700

Data Index: 3459705 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6683. Min Act: -0.1700

Data Index: 37183 (Open Web Text)

Max Activating Token Index: 846

Text #17

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6682. Min Act: -0.1700

Data Index: 6995623 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6682. Min Act: -0.1700

Data Index: 7117760 (Open Web Text)

Max Activating Token Index: 286

Text #19

Max Range: 2.8245. Min Range: -2.8245

Max Act: 2.6611. Min Act: -0.1700

Data Index: 5629610 (Open Web Text)

Max Activating Token Index: 43