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

Dataset: Open Web Text

Neuron 1907 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: 3.6988. Min Range: -3.6988

Max Act: 3.6975. Min Act: -0.1700

Data Index: 8035729 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6954. Min Act: -0.1700

Data Index: 2470328 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6988. Min Act: -0.1700

Data Index: 4321863 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6632. Min Act: -0.1700

Data Index: 7769538 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6465. Min Act: -0.1700

Data Index: 8766798 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6357. Min Act: -0.1700

Data Index: 6851680 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5926. Min Act: -0.1700

Data Index: 3771784 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5874. Min Act: -0.1700

Data Index: 2562980 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5848. Min Act: -0.1700

Data Index: 5478555 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.6055. Min Act: -0.1700

Data Index: 1526849 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5924. Min Act: -0.1700

Data Index: 5433486 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5595. Min Act: -0.1700

Data Index: 6214799 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5767. Min Act: -0.1700

Data Index: 8423867 (Open Web Text)

Max Activating Token Index: 32

Text #13

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5744. Min Act: -0.1700

Data Index: 4341035 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5427. Min Act: -0.1700

Data Index: 4912813 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5610. Min Act: -0.1700

Data Index: 5158034 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5242. Min Act: -0.1700

Data Index: 6320705 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5397. Min Act: -0.1700

Data Index: 4685564 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5359. Min Act: -0.1700

Data Index: 5000525 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.6988. Min Range: -3.6988

Max Act: 3.5422. Min Act: -0.1700

Data Index: 6458527 (Open Web Text)

Max Activating Token Index: 5