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

Dataset: Open Web Text

Neuron 1528 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: 4.8760. Min Range: -4.8760

Max Act: 4.8760. Min Act: -0.1700

Data Index: 7229436 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.8603. Min Act: -0.1700

Data Index: 1578926 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.8496. Min Act: -0.1700

Data Index: 456860 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.8315. Min Act: -0.1700

Data Index: 2887600 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.8353. Min Act: -0.1700

Data Index: 2380816 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.8014. Min Act: -0.1700

Data Index: 8347526 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.8130. Min Act: -0.1700

Data Index: 869311 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7759. Min Act: -0.1700

Data Index: 5208209 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7673. Min Act: -0.1700

Data Index: 1334389 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7566. Min Act: -0.1700

Data Index: 6168280 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7749. Min Act: -0.1700

Data Index: 8156025 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7644. Min Act: -0.1700

Data Index: 3294105 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7733. Min Act: -0.1700

Data Index: 6260689 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7574. Min Act: -0.1700

Data Index: 3708745 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7362. Min Act: -0.1700

Data Index: 5643886 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7301. Min Act: -0.1700

Data Index: 1564748 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7390. Min Act: -0.1700

Data Index: 1989357 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7669. Min Act: -0.1700

Data Index: 475472 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7248. Min Act: -0.1700

Data Index: 885623 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.7455. Min Act: -0.1700

Data Index: 2032276 (Open Web Text)

Max Activating Token Index: 7