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

Dataset: Open Web Text

Neuron 950 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: 4.5943. Min Range: -4.5943

Max Act: 4.5943. Min Act: -0.1700

Data Index: 8725067 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.5339. Min Act: -0.1700

Data Index: 5696984 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.5504. Min Act: -0.1700

Data Index: 913493 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.5427. Min Act: -0.1700

Data Index: 8789325 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.5026. Min Act: -0.1700

Data Index: 1799912 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.5008. Min Act: -0.1700

Data Index: 5374233 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.5199. Min Act: -0.1700

Data Index: 3146157 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.5074. Min Act: -0.1700

Data Index: 573989 (Open Web Text)

Max Activating Token Index: 750

Text #8

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4986. Min Act: -0.1700

Data Index: 127581 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4556. Min Act: -0.1700

Data Index: 7610558 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4373. Min Act: -0.1700

Data Index: 4489165 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4499. Min Act: -0.1700

Data Index: 4580871 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4383. Min Act: -0.1700

Data Index: 1537130 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4487. Min Act: -0.1700

Data Index: 3811203 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4322. Min Act: -0.1700

Data Index: 2097625 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4200. Min Act: -0.1700

Data Index: 5380327 (Open Web Text)

Max Activating Token Index: 23

Text #16

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4257. Min Act: -0.1700

Data Index: 2649198 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4044. Min Act: -0.1700

Data Index: 3912311 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4127. Min Act: -0.1700

Data Index: 6072511 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.5943. Min Range: -4.5943

Max Act: 4.4104. Min Act: -0.1700

Data Index: 7502543 (Open Web Text)

Max Activating Token Index: 13