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

Dataset: Open Web Text

Neuron 1795 in Layer 3

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: 3.8085. Min Range: -3.8085

Max Act: 3.8085. Min Act: -0.1700

Data Index: 2823506 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.7773. Min Act: -0.1700

Data Index: 3619803 (Open Web Text)

Max Activating Token Index: 597

Text #2

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.6917. Min Act: -0.1700

Data Index: 4672081 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.6285. Min Act: -0.1700

Data Index: 6228537 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5705. Min Act: -0.1700

Data Index: 6449427 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5917. Min Act: -0.1700

Data Index: 1239817 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.6020. Min Act: -0.1700

Data Index: 8170119 (Open Web Text)

Max Activating Token Index: 546

Text #7

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.6157. Min Act: -0.1700

Data Index: 6426313 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5515. Min Act: -0.1700

Data Index: 5366171 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5414. Min Act: -0.1700

Data Index: 5689566 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5447. Min Act: -0.1700

Data Index: 8681291 (Open Web Text)

Max Activating Token Index: 84

Text #11

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5527. Min Act: -0.1700

Data Index: 3966168 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5144. Min Act: -0.1700

Data Index: 6445557 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5515. Min Act: -0.1700

Data Index: 7872 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5412. Min Act: -0.1700

Data Index: 6264572 (Open Web Text)

Max Activating Token Index: 699

Text #15

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5515. Min Act: -0.1700

Data Index: 4643921 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5515. Min Act: -0.1700

Data Index: 7677806 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5150. Min Act: -0.1700

Data Index: 5839009 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5706. Min Act: -0.1700

Data Index: 4209367 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 3.8085. Min Range: -3.8085

Max Act: 3.5283. Min Act: -0.1700

Data Index: 6900543 (Open Web Text)

Max Activating Token Index: 57