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

Dataset: Open Web Text

Neuron 1918 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: 0.6927. Min Range: -0.6927

Max Act: 0.6927. Min Act: -0.1700

Data Index: 8072709 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6810. Min Act: -0.1700

Data Index: 7969184 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6851. Min Act: -0.1700

Data Index: 5719975 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6452. Min Act: -0.1700

Data Index: 1803245 (Open Web Text)

Max Activating Token Index: 435

Text #4

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6385. Min Act: -0.1700

Data Index: 8259501 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6294. Min Act: -0.1700

Data Index: 4487694 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6316. Min Act: -0.1700

Data Index: 2138700 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6362. Min Act: -0.1700

Data Index: 2266972 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6279. Min Act: -0.1700

Data Index: 7382964 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6210. Min Act: -0.1700

Data Index: 6068917 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6267. Min Act: -0.1700

Data Index: 6306183 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6152. Min Act: -0.1700

Data Index: 7033937 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6200. Min Act: -0.1700

Data Index: 4487696 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6101. Min Act: -0.1700

Data Index: 8127454 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6122. Min Act: -0.1700

Data Index: 2022498 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6063. Min Act: -0.1700

Data Index: 1882010 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6020. Min Act: -0.1700

Data Index: 5347443 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6020. Min Act: -0.1700

Data Index: 7264218 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5989. Min Act: -0.1700

Data Index: 5824842 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5911. Min Act: -0.1700

Data Index: 2391883 (Open Web Text)

Max Activating Token Index: 878