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

Dataset: Open Web Text

Neuron 331 in Layer 5

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: 3.6623. Min Range: -3.6623

Max Act: 3.6623. Min Act: -0.1700

Data Index: 7194661 (Open Web Text)

Max Activating Token Index: 758

Text #1

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.5816. Min Act: -0.1700

Data Index: 7247572 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.5499. Min Act: -0.1700

Data Index: 4198927 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.5525. Min Act: -0.1700

Data Index: 4300040 (Open Web Text)

Max Activating Token Index: 635

Text #4

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.5616. Min Act: -0.1700

Data Index: 1165566 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.5460. Min Act: -0.1700

Data Index: 2417303 (Open Web Text)

Max Activating Token Index: 327

Text #6

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.5262. Min Act: -0.1700

Data Index: 8467067 (Open Web Text)

Max Activating Token Index: 208

Text #7

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4960. Min Act: -0.1700

Data Index: 7455837 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.5016. Min Act: -0.1700

Data Index: 3871834 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4809. Min Act: -0.1700

Data Index: 3852150 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4472. Min Act: -0.1700

Data Index: 2363043 (Open Web Text)

Max Activating Token Index: 336

Text #11

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4835. Min Act: -0.1700

Data Index: 1893491 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4344. Min Act: -0.1700

Data Index: 7400975 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4316. Min Act: -0.1700

Data Index: 3823074 (Open Web Text)

Max Activating Token Index: 682

Text #14

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.3903. Min Act: -0.1700

Data Index: 2599108 (Open Web Text)

Max Activating Token Index: 854

Text #15

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4538. Min Act: -0.1700

Data Index: 4466106 (Open Web Text)

Max Activating Token Index: 809

Text #16

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4069. Min Act: -0.1700

Data Index: 7118934 (Open Web Text)

Max Activating Token Index: 184

Text #17

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.4111. Min Act: -0.1700

Data Index: 6602865 (Open Web Text)

Max Activating Token Index: 271

Text #18

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1201211 (Open Web Text)

Max Activating Token Index: 989

Text #19

Max Range: 3.6623. Min Range: -3.6623

Max Act: 3.3718. Min Act: -0.1700

Data Index: 4881603 (Open Web Text)

Max Activating Token Index: 143