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

Dataset: Open Web Text

Neuron 3016 in Layer 2

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: 4.8775. Min Range: -4.8775

Max Act: 4.8775. Min Act: -0.1700

Data Index: 2458233 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.8334. Min Act: -0.1700

Data Index: 5433846 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.8198. Min Act: -0.1700

Data Index: 8271735 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7904. Min Act: -0.1700

Data Index: 5936921 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.8130. Min Act: -0.1700

Data Index: 6223512 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.8050. Min Act: -0.1700

Data Index: 2296928 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7889. Min Act: -0.1700

Data Index: 6938205 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7673. Min Act: -0.1700

Data Index: 4720299 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.8167. Min Act: -0.1700

Data Index: 2324113 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7573. Min Act: -0.1700

Data Index: 4023045 (Open Web Text)

Max Activating Token Index: 51

Text #10

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7719. Min Act: -0.1700

Data Index: 8587255 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7324. Min Act: -0.1700

Data Index: 2679505 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7205. Min Act: -0.1700

Data Index: 2899038 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6917. Min Act: -0.1700

Data Index: 7466746 (Open Web Text)

Max Activating Token Index: 56

Text #14

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7045. Min Act: -0.1700

Data Index: 7242917 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6763. Min Act: -0.1700

Data Index: 5203154 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7197. Min Act: -0.1700

Data Index: 7924765 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6770. Min Act: -0.1700

Data Index: 2993827 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6909. Min Act: -0.1700

Data Index: 7063283 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6671. Min Act: -0.1700

Data Index: 1688537 (Open Web Text)

Max Activating Token Index: 30