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

Dataset: Open Web Text

Neuron 2581 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: 3.1833. Min Range: -3.1833

Max Act: 3.1833. Min Act: -0.1700

Data Index: 3250932 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1328. Min Act: -0.1700

Data Index: 3501968 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1305. Min Act: -0.1700

Data Index: 8069941 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1328. Min Act: -0.1700

Data Index: 7531743 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1328. Min Act: -0.1700

Data Index: 4812516 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1328. Min Act: -0.1700

Data Index: 1502020 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1328. Min Act: -0.1700

Data Index: 1739692 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1144. Min Act: -0.1700

Data Index: 7858508 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1206. Min Act: -0.1700

Data Index: 7545515 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1106. Min Act: -0.1700

Data Index: 1594436 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1215. Min Act: -0.1700

Data Index: 5681845 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.1063. Min Act: -0.1700

Data Index: 2678406 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.0946. Min Act: -0.1700

Data Index: 7653368 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.0777. Min Act: -0.1700

Data Index: 6434195 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.0903. Min Act: -0.1700

Data Index: 3075666 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.0705. Min Act: -0.1700

Data Index: 2532261 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.0705. Min Act: -0.1700

Data Index: 2267621 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.0691. Min Act: -0.1700

Data Index: 5999049 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.0610. Min Act: -0.1700

Data Index: 2738304 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.1833. Min Range: -3.1833

Max Act: 3.0726. Min Act: -0.1700

Data Index: 1063952 (Open Web Text)

Max Activating Token Index: 4