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

Dataset: Open Web Text

Neuron 931 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: 2.5279. Min Range: -2.5279

Max Act: 2.5233. Min Act: -0.1700

Data Index: 1800200 (Open Web Text)

Max Activating Token Index: 30

Text #1

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.5250. Min Act: -0.1700

Data Index: 3578041 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.5279. Min Act: -0.1700

Data Index: 1453145 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.5041. Min Act: -0.1700

Data Index: 7547194 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.5116. Min Act: -0.1700

Data Index: 191307 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4958. Min Act: -0.1700

Data Index: 550386 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4972. Min Act: -0.1700

Data Index: 6448293 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4982. Min Act: -0.1700

Data Index: 3541386 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4700. Min Act: -0.1700

Data Index: 7789101 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4726. Min Act: -0.1700

Data Index: 2473911 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4768. Min Act: -0.1700

Data Index: 5669414 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4805. Min Act: -0.1700

Data Index: 5271881 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4711. Min Act: -0.1700

Data Index: 8525279 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4821. Min Act: -0.1700

Data Index: 3295999 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4564. Min Act: -0.1700

Data Index: 6397347 (Open Web Text)

Max Activating Token Index: 622

Text #15

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4581. Min Act: -0.1700

Data Index: 2506066 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4529. Min Act: -0.1700

Data Index: 4448826 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4552. Min Act: -0.1700

Data Index: 4479919 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4713. Min Act: -0.1700

Data Index: 7514901 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.5279. Min Range: -2.5279

Max Act: 2.4640. Min Act: -0.1700

Data Index: 7756564 (Open Web Text)

Max Activating Token Index: 6