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

Dataset: Open Web Text

Neuron 2118 in Layer 1

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: 0.6599. Min Range: -0.6599

Max Act: 0.6599. Min Act: -0.1646

Data Index: 2859179 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6424. Min Act: -0.1692

Data Index: 3558856 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6334. Min Act: -0.1699

Data Index: 7330934 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6068. Min Act: -0.1699

Data Index: 887510 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6095. Min Act: -0.1700

Data Index: 1171137 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6081. Min Act: -0.1700

Data Index: 4934967 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6094. Min Act: -0.1700

Data Index: 6152829 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5960. Min Act: -0.1700

Data Index: 1371877 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5879. Min Act: -0.1699

Data Index: 4867756 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5816. Min Act: -0.1641

Data Index: 1168853 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5753. Min Act: -0.1696

Data Index: 1977037 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5697. Min Act: -0.1691

Data Index: 5386134 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5800. Min Act: -0.1700

Data Index: 1110998 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5721. Min Act: -0.1658

Data Index: 1321914 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5621. Min Act: -0.1699

Data Index: 8261303 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5569. Min Act: -0.1697

Data Index: 6633974 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5612. Min Act: -0.1696

Data Index: 3314253 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5607. Min Act: -0.1636

Data Index: 8587343 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5611. Min Act: -0.1700

Data Index: 4156043 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5541. Min Act: -0.1684

Data Index: 1008722 (Open Web Text)

Max Activating Token Index: 7