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

Dataset: Open Web Text

Neuron 2781 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: 2.6944. Min Range: -2.6944

Max Act: 2.6944. Min Act: -0.1700

Data Index: 8397139 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.6329. Min Act: -0.1700

Data Index: 2623928 (Open Web Text)

Max Activating Token Index: 24

Text #2

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.6324. Min Act: -0.1700

Data Index: 5604940 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.6294. Min Act: -0.1700

Data Index: 5692355 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.6221. Min Act: -0.1700

Data Index: 6599150 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.6173. Min Act: -0.1700

Data Index: 8243752 (Open Web Text)

Max Activating Token Index: 265

Text #6

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5982. Min Act: -0.1700

Data Index: 5924615 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5986. Min Act: -0.1700

Data Index: 4497177 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.6040. Min Act: -0.1700

Data Index: 1529350 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5799. Min Act: -0.1700

Data Index: 2724155 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5790. Min Act: -0.1700

Data Index: 6427211 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5740. Min Act: -0.1700

Data Index: 4243511 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5744. Min Act: -0.1700

Data Index: 1722904 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5881. Min Act: -0.1700

Data Index: 2894960 (Open Web Text)

Max Activating Token Index: 68

Text #14

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5783. Min Act: -0.1700

Data Index: 5911199 (Open Web Text)

Max Activating Token Index: 49

Text #15

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5822. Min Act: -0.1700

Data Index: 1128453 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5824. Min Act: -0.1700

Data Index: 6630671 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5770. Min Act: -0.1700

Data Index: 6770957 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5826. Min Act: -0.1700

Data Index: 7685858 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.6944. Min Range: -2.6944

Max Act: 2.5789. Min Act: -0.1700

Data Index: 4691553 (Open Web Text)

Max Activating Token Index: 6