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

Dataset: Open Web Text

Neuron 2673 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: 3.8944. Min Range: -3.8944

Max Act: 3.8944. Min Act: -0.1700

Data Index: 7339074 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.8944. Min Act: -0.1700

Data Index: 2546439 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.8598. Min Act: -0.1700

Data Index: 3457276 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.8427. Min Act: -0.1700

Data Index: 5311167 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.8153. Min Act: -0.1700

Data Index: 4385700 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7649. Min Act: -0.1700

Data Index: 2759156 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7802. Min Act: -0.1700

Data Index: 4659792 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7684. Min Act: -0.1700

Data Index: 734827 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7961. Min Act: -0.1700

Data Index: 8790476 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7955. Min Act: -0.1700

Data Index: 388079 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7504. Min Act: -0.1700

Data Index: 5924494 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7412. Min Act: -0.1700

Data Index: 6971363 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7622. Min Act: -0.1700

Data Index: 7288614 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7699. Min Act: -0.1700

Data Index: 3867280 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7699. Min Act: -0.1700

Data Index: 3893830 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7243. Min Act: -0.1700

Data Index: 2361558 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7007. Min Act: -0.1700

Data Index: 4392903 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.6977. Min Act: -0.1700

Data Index: 397521 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7246. Min Act: -0.1700

Data Index: 4850448 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7441. Min Act: -0.1700

Data Index: 3885482 (Open Web Text)

Max Activating Token Index: 4