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

Dataset: Open Web Text

Neuron 2252 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: 1.8587. Min Range: -1.8587

Max Act: 1.8587. Min Act: -0.1700

Data Index: 3463273 (Open Web Text)

Max Activating Token Index: 533

Text #1

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.8198. Min Act: -0.1700

Data Index: 1508252 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.8077. Min Act: -0.1700

Data Index: 2635430 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.8012. Min Act: -0.1700

Data Index: 2069216 (Open Web Text)

Max Activating Token Index: 958

Text #4

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.8034. Min Act: -0.1700

Data Index: 876068 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7863. Min Act: -0.1700

Data Index: 5282303 (Open Web Text)

Max Activating Token Index: 970

Text #6

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7694. Min Act: -0.1700

Data Index: 8219865 (Open Web Text)

Max Activating Token Index: 566

Text #7

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7587. Min Act: -0.1700

Data Index: 8244970 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7836. Min Act: -0.1700

Data Index: 8050836 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7768. Min Act: -0.1700

Data Index: 7097893 (Open Web Text)

Max Activating Token Index: 923

Text #10

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7808. Min Act: -0.1700

Data Index: 187126 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7778. Min Act: -0.1700

Data Index: 2084621 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7810. Min Act: -0.1700

Data Index: 5914129 (Open Web Text)

Max Activating Token Index: 217

Text #13

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7562. Min Act: -0.1700

Data Index: 4311945 (Open Web Text)

Max Activating Token Index: 495

Text #14

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7618. Min Act: -0.1700

Data Index: 6648969 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7651. Min Act: -0.1700

Data Index: 5072519 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7470. Min Act: -0.1700

Data Index: 6189558 (Open Web Text)

Max Activating Token Index: 522

Text #17

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7606. Min Act: -0.1700

Data Index: 1547856 (Open Web Text)

Max Activating Token Index: 867

Text #18

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7511. Min Act: -0.1700

Data Index: 946401 (Open Web Text)

Max Activating Token Index: 837

Text #19

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7584. Min Act: -0.1700

Data Index: 237864 (Open Web Text)

Max Activating Token Index: 11