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

Dataset: Open Web Text

Neuron 209 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: 1.9709. Min Range: -1.9709

Max Act: 1.9709. Min Act: -0.1700

Data Index: 2510077 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9404. Min Act: -0.1700

Data Index: 2015187 (Open Web Text)

Max Activating Token Index: 312

Text #2

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9065. Min Act: -0.1700

Data Index: 8787260 (Open Web Text)

Max Activating Token Index: 444

Text #3

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9254. Min Act: -0.1700

Data Index: 1819020 (Open Web Text)

Max Activating Token Index: 618

Text #4

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8992. Min Act: -0.1700

Data Index: 8147063 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9037. Min Act: -0.1700

Data Index: 7574587 (Open Web Text)

Max Activating Token Index: 730

Text #6

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9180. Min Act: -0.1700

Data Index: 4784412 (Open Web Text)

Max Activating Token Index: 728

Text #7

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.9046. Min Act: -0.1700

Data Index: 790548 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8974. Min Act: -0.1700

Data Index: 3225119 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8859. Min Act: -0.1700

Data Index: 7193861 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8863. Min Act: -0.1700

Data Index: 3264662 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8808. Min Act: -0.1700

Data Index: 5644121 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8808. Min Act: -0.1700

Data Index: 8147395 (Open Web Text)

Max Activating Token Index: 192

Text #13

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8819. Min Act: -0.1700

Data Index: 8020723 (Open Web Text)

Max Activating Token Index: 550

Text #14

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8611. Min Act: -0.1700

Data Index: 1730470 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8772. Min Act: -0.1700

Data Index: 1914191 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8765. Min Act: -0.1700

Data Index: 1518959 (Open Web Text)

Max Activating Token Index: 213

Text #17

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8627. Min Act: -0.1700

Data Index: 6131352 (Open Web Text)

Max Activating Token Index: 222

Text #18

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8547. Min Act: -0.1700

Data Index: 8758074 (Open Web Text)

Max Activating Token Index: 517

Text #19

Max Range: 1.9709. Min Range: -1.9709

Max Act: 1.8616. Min Act: -0.1700

Data Index: 7780777 (Open Web Text)

Max Activating Token Index: 410