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

Dataset: Open Web Text

Neuron 2786 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: 2.8284. Min Range: -2.8284

Max Act: 2.8284. Min Act: -0.1700

Data Index: 2142311 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.7087. Min Act: -0.1700

Data Index: 6805342 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.7167. Min Act: -0.1700

Data Index: 7156962 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6968. Min Act: -0.1700

Data Index: 6974968 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.7063. Min Act: -0.1700

Data Index: 7236835 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6801. Min Act: -0.1700

Data Index: 76903 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6823. Min Act: -0.1700

Data Index: 12585 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6783. Min Act: -0.1700

Data Index: 1126908 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6889. Min Act: -0.1700

Data Index: 2075542 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6939. Min Act: -0.1700

Data Index: 2597238 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6722. Min Act: -0.1700

Data Index: 6804205 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6746. Min Act: -0.1700

Data Index: 607910 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6663. Min Act: -0.1700

Data Index: 700813 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6741. Min Act: -0.1700

Data Index: 4821224 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6616. Min Act: -0.1700

Data Index: 3567243 (Open Web Text)

Max Activating Token Index: 621

Text #15

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6472. Min Act: -0.1700

Data Index: 494847 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6561. Min Act: -0.1700

Data Index: 4903761 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6525. Min Act: -0.1700

Data Index: 3329055 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6454. Min Act: -0.1700

Data Index: 491112 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.8284. Min Range: -2.8284

Max Act: 2.6497. Min Act: -0.1700

Data Index: 2875378 (Open Web Text)

Max Activating Token Index: 8