Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 5477 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6771. Min Act: -0.1698

Data Index: 5831585 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6684. Min Act: -0.1684

Data Index: 5576160 (Open Web Text)

Max Activating Token Index: 761

Text #2

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6423. Min Act: -0.1699

Data Index: 5844138 (Open Web Text)

Max Activating Token Index: 705

Text #3

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6249. Min Act: -0.1514

Data Index: 5576163 (Open Web Text)

Max Activating Token Index: 718

Text #4

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6249. Min Act: -0.1700

Data Index: 6348368 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.6249. Min Act: -0.1315

Data Index: 7332229 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5987. Min Act: -0.1698

Data Index: 5716678 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5899. Min Act: -0.1613

Data Index: 5576157 (Open Web Text)

Max Activating Token Index: 803

Text #8

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5899. Min Act: -0.1160

Data Index: 7332228 (Open Web Text)

Max Activating Token Index: 756

Text #9

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5812. Min Act: -0.1669

Data Index: 6357284 (Open Web Text)

Max Activating Token Index: 771

Text #10

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5725. Min Act: -0.1700

Data Index: 6357288 (Open Web Text)

Max Activating Token Index: 759

Text #11

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5725. Min Act: -0.1677

Data Index: 5576156 (Open Web Text)

Max Activating Token Index: 735

Text #12

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5637. Min Act: -0.1700

Data Index: 3547276 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5637. Min Act: -0.1700

Data Index: 211997 (Open Web Text)

Max Activating Token Index: 776

Text #14

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5637. Min Act: -0.1643

Data Index: 7818232 (Open Web Text)

Max Activating Token Index: 758

Text #15

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5637. Min Act: -0.1643

Data Index: 3879769 (Open Web Text)

Max Activating Token Index: 701

Text #16

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5550. Min Act: -0.1697

Data Index: 4477731 (Open Web Text)

Max Activating Token Index: 743

Text #17

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5462. Min Act: -0.1561

Data Index: 5576159 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5462. Min Act: -0.1345

Data Index: 298970 (Open Web Text)

Max Activating Token Index: 729

Text #19

Max Range: 1.6771. Min Range: -1.6771

Max Act: 1.5374. Min Act: -0.1588

Data Index: 3490484 (Open Web Text)

Max Activating Token Index: 660