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

Dataset: Open Web Text

Neuron 3671 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6771. Min Act: -0.1700

Data Index: 6168060 (Open Web Text)

Max Activating Token Index: 420

Text #1

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5050. Min Act: -0.1700

Data Index: 6099072 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5050. Min Act: -0.1700

Data Index: 2613688 (Open Web Text)

Max Activating Token Index: 593

Text #3

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4893. Min Act: -0.1700

Data Index: 7855106 (Open Web Text)

Max Activating Token Index: 746

Text #4

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4736. Min Act: -0.1700

Data Index: 8018850 (Open Web Text)

Max Activating Token Index: 759

Text #5

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4736. Min Act: -0.1700

Data Index: 7720199 (Open Web Text)

Max Activating Token Index: 515

Text #6

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4109. Min Act: -0.1700

Data Index: 3696033 (Open Web Text)

Max Activating Token Index: 980

Text #7

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.4109. Min Act: -0.1700

Data Index: 6816329 (Open Web Text)

Max Activating Token Index: 704

Text #8

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3796. Min Act: -0.1700

Data Index: 3713349 (Open Web Text)

Max Activating Token Index: 967

Text #9

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3953. Min Act: -0.1700

Data Index: 201587 (Open Web Text)

Max Activating Token Index: 602

Text #10

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3796. Min Act: -0.1700

Data Index: 6287390 (Open Web Text)

Max Activating Token Index: 344

Text #11

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3639. Min Act: -0.1700

Data Index: 2052323 (Open Web Text)

Max Activating Token Index: 695

Text #12

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3639. Min Act: -0.1700

Data Index: 4291111 (Open Web Text)

Max Activating Token Index: 825

Text #13

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3639. Min Act: -0.1700

Data Index: 4062544 (Open Web Text)

Max Activating Token Index: 806

Text #14

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3482. Min Act: -0.1700

Data Index: 8699678 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3639. Min Act: -0.1700

Data Index: 8120918 (Open Web Text)

Max Activating Token Index: 815

Text #16

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3482. Min Act: -0.1700

Data Index: 8704810 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3482. Min Act: -0.1700

Data Index: 7399724 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3482. Min Act: -0.1700

Data Index: 1236530 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.3168. Min Act: -0.1700

Data Index: 2238120 (Open Web Text)

Max Activating Token Index: 499