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

Dataset: Open Web Text

Neuron 686 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: 4.1955. Min Range: -4.1955

Max Act: 4.1955. Min Act: -0.1700

Data Index: 5620439 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.1781. Min Act: -0.1700

Data Index: 3272890 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.1653. Min Act: -0.1700

Data Index: 3744176 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.1230. Min Act: -0.1700

Data Index: 233756 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.1122. Min Act: -0.1700

Data Index: 4490674 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.1123. Min Act: -0.1700

Data Index: 7977292 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0909. Min Act: -0.1700

Data Index: 4799444 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0948. Min Act: -0.1700

Data Index: 7955102 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0745. Min Act: -0.1700

Data Index: 4952908 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.1032. Min Act: -0.1700

Data Index: 6729291 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0474. Min Act: -0.1700

Data Index: 6033741 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0746. Min Act: -0.1700

Data Index: 625384 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0631. Min Act: -0.1700

Data Index: 6903499 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0487. Min Act: -0.1700

Data Index: 8733396 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0347. Min Act: -0.1700

Data Index: 6412742 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0160. Min Act: -0.1700

Data Index: 7597292 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0184. Min Act: -0.1700

Data Index: 7878205 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0196. Min Act: -0.1700

Data Index: 6038246 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0215. Min Act: -0.1700

Data Index: 4267845 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.1955. Min Range: -4.1955

Max Act: 4.0193. Min Act: -0.1700

Data Index: 5947265 (Open Web Text)

Max Activating Token Index: 19