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

Dataset: Open Web Text

Neuron 1195 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: 2.2938. Min Range: -2.2938

Max Act: 2.2938. Min Act: -0.1700

Data Index: 7722535 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.2364. Min Act: -0.1700

Data Index: 117009 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1883. Min Act: -0.1700

Data Index: 8801784 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1842. Min Act: -0.1700

Data Index: 5744734 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1827. Min Act: -0.1700

Data Index: 6500151 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1681. Min Act: -0.1700

Data Index: 472087 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1560. Min Act: -0.1700

Data Index: 4397218 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1613. Min Act: -0.1700

Data Index: 7591962 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1687. Min Act: -0.1700

Data Index: 6562309 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1594. Min Act: -0.1700

Data Index: 497386 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1580. Min Act: -0.1700

Data Index: 5317349 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1540. Min Act: -0.1700

Data Index: 8484083 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1555. Min Act: -0.1700

Data Index: 4925586 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1600. Min Act: -0.1700

Data Index: 4908682 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1368. Min Act: -0.1700

Data Index: 6475864 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1542. Min Act: -0.1700

Data Index: 6472712 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1545. Min Act: -0.1700

Data Index: 6409637 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1490. Min Act: -0.1700

Data Index: 849745 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1442. Min Act: -0.1700

Data Index: 2238924 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.2938. Min Range: -2.2938

Max Act: 2.1324. Min Act: -0.1700

Data Index: 4901847 (Open Web Text)

Max Activating Token Index: 3