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

Dataset: Open Web Text

Neuron 510 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: 2.9557. Min Range: -2.9557

Max Act: 2.9557. Min Act: -0.1700

Data Index: 3742692 (Open Web Text)

Max Activating Token Index: 981

Text #1

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.9387. Min Act: -0.1700

Data Index: 3960415 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8793. Min Act: -0.1700

Data Index: 5593434 (Open Web Text)

Max Activating Token Index: 987

Text #3

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8915. Min Act: -0.1700

Data Index: 1541532 (Open Web Text)

Max Activating Token Index: 89

Text #4

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8907. Min Act: -0.1700

Data Index: 8794165 (Open Web Text)

Max Activating Token Index: 198

Text #5

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8842. Min Act: -0.1700

Data Index: 661558 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8785. Min Act: -0.1700

Data Index: 8153722 (Open Web Text)

Max Activating Token Index: 430

Text #7

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8636. Min Act: -0.1700

Data Index: 2424133 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8329. Min Act: -0.1700

Data Index: 4442906 (Open Web Text)

Max Activating Token Index: 258

Text #9

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8110. Min Act: -0.1700

Data Index: 5166593 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8354. Min Act: -0.1700

Data Index: 6276393 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8276. Min Act: -0.1700

Data Index: 8508594 (Open Web Text)

Max Activating Token Index: 291

Text #12

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8112. Min Act: -0.1700

Data Index: 5930995 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.7923. Min Act: -0.1700

Data Index: 4121833 (Open Web Text)

Max Activating Token Index: 845

Text #14

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8225. Min Act: -0.1700

Data Index: 7429220 (Open Web Text)

Max Activating Token Index: 448

Text #15

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.7987. Min Act: -0.1700

Data Index: 3154767 (Open Web Text)

Max Activating Token Index: 503

Text #16

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.7877. Min Act: -0.1700

Data Index: 750780 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.8007. Min Act: -0.1700

Data Index: 3864729 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.7869. Min Act: -0.1700

Data Index: 8705521 (Open Web Text)

Max Activating Token Index: 477

Text #19

Max Range: 2.9557. Min Range: -2.9557

Max Act: 2.7788. Min Act: -0.1700

Data Index: 862418 (Open Web Text)

Max Activating Token Index: 150