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

Dataset: Open Web Text

Neuron 1538 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: 1.9620. Min Range: -1.9620

Max Act: 1.9620. Min Act: -0.1700

Data Index: 4438160 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9528. Min Act: -0.1700

Data Index: 4690402 (Open Web Text)

Max Activating Token Index: 51

Text #2

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9362. Min Act: -0.1700

Data Index: 8037328 (Open Web Text)

Max Activating Token Index: 603

Text #3

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9236. Min Act: -0.1700

Data Index: 1888043 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9245. Min Act: -0.1700

Data Index: 3060301 (Open Web Text)

Max Activating Token Index: 496

Text #5

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9039. Min Act: -0.1700

Data Index: 1982222 (Open Web Text)

Max Activating Token Index: 800

Text #6

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9137. Min Act: -0.1700

Data Index: 8179943 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9038. Min Act: -0.1700

Data Index: 4087801 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9075. Min Act: -0.1689

Data Index: 4924535 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8862. Min Act: -0.1700

Data Index: 2435210 (Open Web Text)

Max Activating Token Index: 474

Text #10

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8916. Min Act: -0.1700

Data Index: 7171866 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8973. Min Act: -0.1700

Data Index: 1795714 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8800. Min Act: -0.1700

Data Index: 6325940 (Open Web Text)

Max Activating Token Index: 122

Text #13

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8827. Min Act: -0.1700

Data Index: 4076114 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8843. Min Act: -0.1699

Data Index: 1031757 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8773. Min Act: -0.1698

Data Index: 4707114 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8903. Min Act: -0.1700

Data Index: 7905664 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8689. Min Act: -0.1700

Data Index: 7186880 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8857. Min Act: -0.1700

Data Index: 6371109 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8725. Min Act: -0.1700

Data Index: 5608857 (Open Web Text)

Max Activating Token Index: 148