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

Dataset: Open Web Text

Neuron 516 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: 2.9072. Min Range: -2.9072

Max Act: 2.9072. Min Act: -0.1700

Data Index: 8270144 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.8909. Min Act: -0.1700

Data Index: 8603812 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.8480. Min Act: -0.1700

Data Index: 8193981 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.8411. Min Act: -0.1700

Data Index: 4240664 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.8137. Min Act: -0.1700

Data Index: 4957703 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.8088. Min Act: -0.1700

Data Index: 8218941 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7990. Min Act: -0.1700

Data Index: 4547705 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.8014. Min Act: -0.1700

Data Index: 5651058 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.8024. Min Act: -0.1700

Data Index: 2797356 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7990. Min Act: -0.1700

Data Index: 207725 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7893. Min Act: -0.1700

Data Index: 6409485 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7815. Min Act: -0.1700

Data Index: 3144206 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7838. Min Act: -0.1700

Data Index: 206974 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7925. Min Act: -0.1700

Data Index: 5531936 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7885. Min Act: -0.1700

Data Index: 569207 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7872. Min Act: -0.1700

Data Index: 8194590 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7746. Min Act: -0.1700

Data Index: 2588760 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7624. Min Act: -0.1700

Data Index: 6789791 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7640. Min Act: -0.1700

Data Index: 6623739 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9072. Min Range: -2.9072

Max Act: 2.7619. Min Act: -0.1700

Data Index: 512638 (Open Web Text)

Max Activating Token Index: 9