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

Dataset: Open Web Text

Neuron 331 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: 3.1535. Min Range: -3.1535

Max Act: 3.1535. Min Act: -0.1700

Data Index: 6364934 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.1437. Min Act: -0.1700

Data Index: 2364176 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.1209. Min Act: -0.1700

Data Index: 1548261 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.1077. Min Act: -0.1700

Data Index: 5139708 (Open Web Text)

Max Activating Token Index: 963

Text #4

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.1221. Min Act: -0.1700

Data Index: 1798121 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.1034. Min Act: -0.1700

Data Index: 7872127 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.1037. Min Act: -0.1700

Data Index: 4964159 (Open Web Text)

Max Activating Token Index: 936

Text #7

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.1022. Min Act: -0.1700

Data Index: 5571711 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0914. Min Act: -0.1700

Data Index: 2729016 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0919. Min Act: -0.1700

Data Index: 8301025 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0895. Min Act: -0.1700

Data Index: 2939982 (Open Web Text)

Max Activating Token Index: 617

Text #11

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.1056. Min Act: -0.1700

Data Index: 629263 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0811. Min Act: -0.1700

Data Index: 236830 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0942. Min Act: -0.1700

Data Index: 5496494 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0597. Min Act: -0.1700

Data Index: 4398410 (Open Web Text)

Max Activating Token Index: 879

Text #15

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0789. Min Act: -0.1700

Data Index: 1332951 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0621. Min Act: -0.1700

Data Index: 6127780 (Open Web Text)

Max Activating Token Index: 263

Text #17

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0935. Min Act: -0.1700

Data Index: 4458306 (Open Web Text)

Max Activating Token Index: 985

Text #18

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0880. Min Act: -0.1700

Data Index: 809126 (Open Web Text)

Max Activating Token Index: 829

Text #19

Max Range: 3.1535. Min Range: -3.1535

Max Act: 3.0706. Min Act: -0.1700

Data Index: 664481 (Open Web Text)

Max Activating Token Index: 602