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

Dataset: Open Web Text

Neuron 2269 in Layer 2

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: 3.6592. Min Range: -3.6592

Max Act: 3.6592. Min Act: -0.1700

Data Index: 2350673 (Open Web Text)

Max Activating Token Index: 1018

Text #1

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.5331. Min Act: -0.1700

Data Index: 947528 (Open Web Text)

Max Activating Token Index: 515

Text #2

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.5186. Min Act: -0.1700

Data Index: 3781420 (Open Web Text)

Max Activating Token Index: 279

Text #3

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.4994. Min Act: -0.1700

Data Index: 3590818 (Open Web Text)

Max Activating Token Index: 504

Text #4

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.4826. Min Act: -0.1700

Data Index: 7263220 (Open Web Text)

Max Activating Token Index: 662

Text #5

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.5011. Min Act: -0.1700

Data Index: 1390727 (Open Web Text)

Max Activating Token Index: 913

Text #6

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.4583. Min Act: -0.1700

Data Index: 326670 (Open Web Text)

Max Activating Token Index: 966

Text #7

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.4399. Min Act: -0.1700

Data Index: 5947805 (Open Web Text)

Max Activating Token Index: 871

Text #8

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.4017. Min Act: -0.1700

Data Index: 1550165 (Open Web Text)

Max Activating Token Index: 822

Text #9

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.4111. Min Act: -0.1700

Data Index: 1567865 (Open Web Text)

Max Activating Token Index: 602

Text #10

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3763. Min Act: -0.1700

Data Index: 222044 (Open Web Text)

Max Activating Token Index: 358

Text #11

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.4061. Min Act: -0.1700

Data Index: 3597571 (Open Web Text)

Max Activating Token Index: 134

Text #12

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3675. Min Act: -0.1700

Data Index: 4000600 (Open Web Text)

Max Activating Token Index: 785

Text #13

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3617. Min Act: -0.1700

Data Index: 578984 (Open Web Text)

Max Activating Token Index: 920

Text #14

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3620. Min Act: -0.1700

Data Index: 6775904 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3571. Min Act: -0.1700

Data Index: 2452150 (Open Web Text)

Max Activating Token Index: 164

Text #16

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3659. Min Act: -0.1700

Data Index: 2246606 (Open Web Text)

Max Activating Token Index: 792

Text #17

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3551. Min Act: -0.1700

Data Index: 6711256 (Open Web Text)

Max Activating Token Index: 621

Text #18

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3715. Min Act: -0.1700

Data Index: 1567856 (Open Web Text)

Max Activating Token Index: 625

Text #19

Max Range: 3.6592. Min Range: -3.6592

Max Act: 3.3447. Min Act: -0.1700

Data Index: 2300829 (Open Web Text)

Max Activating Token Index: 218