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

Dataset: Open Web Text

Neuron 2012 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: 1.6733. Min Range: -1.6733

Max Act: 1.6733. Min Act: -0.1700

Data Index: 6333225 (Open Web Text)

Max Activating Token Index: 764

Text #1

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6595. Min Act: -0.1700

Data Index: 7885826 (Open Web Text)

Max Activating Token Index: 445

Text #2

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6597. Min Act: -0.1700

Data Index: 3705275 (Open Web Text)

Max Activating Token Index: 73

Text #3

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6475. Min Act: -0.1700

Data Index: 6838049 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6560. Min Act: -0.1700

Data Index: 5977418 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6414. Min Act: -0.1700

Data Index: 6912300 (Open Web Text)

Max Activating Token Index: 613

Text #6

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6423. Min Act: -0.1700

Data Index: 5070458 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6513. Min Act: -0.1700

Data Index: 6036468 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6229. Min Act: -0.1700

Data Index: 5904171 (Open Web Text)

Max Activating Token Index: 561

Text #9

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6255. Min Act: -0.1700

Data Index: 1104044 (Open Web Text)

Max Activating Token Index: 423

Text #10

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6306. Min Act: -0.1700

Data Index: 25788 (Open Web Text)

Max Activating Token Index: 76

Text #11

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6207. Min Act: -0.1700

Data Index: 18965 (Open Web Text)

Max Activating Token Index: 984

Text #12

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6205. Min Act: -0.1700

Data Index: 4645069 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6178. Min Act: -0.1698

Data Index: 6424598 (Open Web Text)

Max Activating Token Index: 530

Text #14

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6158. Min Act: -0.1700

Data Index: 8700585 (Open Web Text)

Max Activating Token Index: 403

Text #15

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6170. Min Act: -0.1700

Data Index: 498752 (Open Web Text)

Max Activating Token Index: 217

Text #16

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6216. Min Act: -0.1700

Data Index: 2614264 (Open Web Text)

Max Activating Token Index: 857

Text #17

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6107. Min Act: -0.1700

Data Index: 4451087 (Open Web Text)

Max Activating Token Index: 986

Text #18

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6059. Min Act: -0.1700

Data Index: 4260518 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 1.6733. Min Range: -1.6733

Max Act: 1.6057. Min Act: -0.1700

Data Index: 5804040 (Open Web Text)

Max Activating Token Index: 533