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

Dataset: Open Web Text

Neuron 2816 in Layer 0

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: 1.6474. Min Range: -1.6474

Max Act: 1.6474. Min Act: -0.1678

Data Index: 7051646 (Open Web Text)

Max Activating Token Index: 469

Text #1

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.6340. Min Act: -0.1675

Data Index: 2118324 (Open Web Text)

Max Activating Token Index: 784

Text #2

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.6269. Min Act: -0.1675

Data Index: 2118328 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.6123. Min Act: -0.1675

Data Index: 542294 (Open Web Text)

Max Activating Token Index: 866

Text #4

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.6110. Min Act: -0.1675

Data Index: 1489164 (Open Web Text)

Max Activating Token Index: 617

Text #5

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.6072. Min Act: -0.1675

Data Index: 3865599 (Open Web Text)

Max Activating Token Index: 536

Text #6

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5979. Min Act: -0.1675

Data Index: 6381947 (Open Web Text)

Max Activating Token Index: 646

Text #7

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5875. Min Act: -0.1675

Data Index: 8615233 (Open Web Text)

Max Activating Token Index: 955

Text #8

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5978. Min Act: -0.1675

Data Index: 3511537 (Open Web Text)

Max Activating Token Index: 515

Text #9

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.6035. Min Act: -0.1675

Data Index: 494698 (Open Web Text)

Max Activating Token Index: 469

Text #10

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5913. Min Act: -0.1675

Data Index: 3777849 (Open Web Text)

Max Activating Token Index: 525

Text #11

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5857. Min Act: -0.1675

Data Index: 8151076 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5886. Min Act: -0.1675

Data Index: 8089159 (Open Web Text)

Max Activating Token Index: 614

Text #13

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5902. Min Act: -0.1675

Data Index: 6895347 (Open Web Text)

Max Activating Token Index: 767

Text #14

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5887. Min Act: -0.1675

Data Index: 4597071 (Open Web Text)

Max Activating Token Index: 587

Text #15

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5807. Min Act: -0.1675

Data Index: 704352 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5800. Min Act: -0.1675

Data Index: 6758880 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5829. Min Act: -0.1675

Data Index: 743476 (Open Web Text)

Max Activating Token Index: 854

Text #18

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5817. Min Act: -0.1675

Data Index: 6691586 (Open Web Text)

Max Activating Token Index: 521

Text #19

Max Range: 1.6474. Min Range: -1.6474

Max Act: 1.5819. Min Act: -0.1675

Data Index: 3261410 (Open Web Text)

Max Activating Token Index: 479