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

Dataset: Open Web Text

Neuron 3044 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: 4.3281. Min Range: -4.3281

Max Act: 4.3281. Min Act: -0.1700

Data Index: 3967699 (Open Web Text)

Max Activating Token Index: 812

Text #1

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.2904. Min Act: -0.1700

Data Index: 7145728 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.2167. Min Act: -0.1700

Data Index: 46054 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1687. Min Act: -0.1700

Data Index: 6865049 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1508. Min Act: -0.1700

Data Index: 5327475 (Open Web Text)

Max Activating Token Index: 450

Text #5

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1703. Min Act: -0.1700

Data Index: 4887447 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1850. Min Act: -0.1700

Data Index: 4245672 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1864. Min Act: -0.1700

Data Index: 8125703 (Open Web Text)

Max Activating Token Index: 383

Text #8

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1685. Min Act: -0.1700

Data Index: 1661285 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1733. Min Act: -0.1700

Data Index: 3660858 (Open Web Text)

Max Activating Token Index: 137

Text #10

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1554. Min Act: -0.1700

Data Index: 4627998 (Open Web Text)

Max Activating Token Index: 59

Text #11

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1764. Min Act: -0.1700

Data Index: 6330641 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1130. Min Act: -0.1700

Data Index: 3106786 (Open Web Text)

Max Activating Token Index: 404

Text #13

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1109. Min Act: -0.1700

Data Index: 7781166 (Open Web Text)

Max Activating Token Index: 874

Text #14

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.1233. Min Act: -0.1700

Data Index: 2294746 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0843. Min Act: -0.1700

Data Index: 2099405 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0938. Min Act: -0.1700

Data Index: 781513 (Open Web Text)

Max Activating Token Index: 53

Text #17

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0918. Min Act: -0.1700

Data Index: 4306116 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0843. Min Act: -0.1700

Data Index: 5404877 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 4.3281. Min Range: -4.3281

Max Act: 4.0726. Min Act: -0.1700

Data Index: 1459326 (Open Web Text)

Max Activating Token Index: 749