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

Dataset: Open Web Text

Neuron 1408 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: 6.3486. Min Range: -6.3486

Max Act: 6.3486. Min Act: -0.1700

Data Index: 7833060 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.3247. Min Act: -0.1700

Data Index: 3641330 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.2532. Min Act: -0.1700

Data Index: 7011223 (Open Web Text)

Max Activating Token Index: 27

Text #3

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.2498. Min Act: -0.1700

Data Index: 3371261 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.2401. Min Act: -0.1700

Data Index: 3773393 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.2644. Min Act: -0.1700

Data Index: 2909352 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.2154. Min Act: -0.1700

Data Index: 1609599 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1912. Min Act: -0.1700

Data Index: 3077934 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1834. Min Act: -0.1700

Data Index: 634166 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1481. Min Act: -0.1700

Data Index: 8378281 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1663. Min Act: -0.1699

Data Index: 5660885 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1568. Min Act: -0.1700

Data Index: 3482487 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1723. Min Act: -0.1700

Data Index: 3405453 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1685. Min Act: -0.1700

Data Index: 3401507 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1567. Min Act: -0.1700

Data Index: 931742 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1623. Min Act: -0.1700

Data Index: 1896542 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1455. Min Act: -0.1700

Data Index: 4116555 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1513. Min Act: -0.1700

Data Index: 8430862 (Open Web Text)

Max Activating Token Index: 53

Text #18

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1274. Min Act: -0.1700

Data Index: 823398 (Open Web Text)

Max Activating Token Index: 719

Text #19

Max Range: 6.3486. Min Range: -6.3486

Max Act: 6.1208. Min Act: -0.1700

Data Index: 5906035 (Open Web Text)

Max Activating Token Index: 20