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

Dataset: Open Web Text

Neuron 2617 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: 3.5706. Min Range: -3.5706

Max Act: 3.5706. Min Act: -0.1700

Data Index: 6689522 (Open Web Text)

Max Activating Token Index: 877

Text #1

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.5277. Min Act: -0.1700

Data Index: 4132646 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.5171. Min Act: -0.1700

Data Index: 1889998 (Open Web Text)

Max Activating Token Index: 131

Text #3

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.5072. Min Act: -0.1700

Data Index: 7285117 (Open Web Text)

Max Activating Token Index: 132

Text #4

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.4674. Min Act: -0.1700

Data Index: 4132648 (Open Web Text)

Max Activating Token Index: 333

Text #5

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.4768. Min Act: -0.1700

Data Index: 2253685 (Open Web Text)

Max Activating Token Index: 594

Text #6

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.4901. Min Act: -0.1700

Data Index: 6422330 (Open Web Text)

Max Activating Token Index: 717

Text #7

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.4498. Min Act: -0.1700

Data Index: 1627578 (Open Web Text)

Max Activating Token Index: 155

Text #8

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.4280. Min Act: -0.1700

Data Index: 2554415 (Open Web Text)

Max Activating Token Index: 526

Text #9

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3942. Min Act: -0.1700

Data Index: 4356013 (Open Web Text)

Max Activating Token Index: 477

Text #10

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3886. Min Act: -0.1700

Data Index: 4819003 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3999. Min Act: -0.1700

Data Index: 5087998 (Open Web Text)

Max Activating Token Index: 46

Text #12

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.4541. Min Act: -0.1700

Data Index: 4574583 (Open Web Text)

Max Activating Token Index: 441

Text #13

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3691. Min Act: -0.1700

Data Index: 7188229 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3667. Min Act: -0.1700

Data Index: 2344240 (Open Web Text)

Max Activating Token Index: 858

Text #15

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3930. Min Act: -0.1700

Data Index: 4622011 (Open Web Text)

Max Activating Token Index: 500

Text #16

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.4229. Min Act: -0.1700

Data Index: 3888613 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3697. Min Act: -0.1700

Data Index: 1835077 (Open Web Text)

Max Activating Token Index: 932

Text #18

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3855. Min Act: -0.1700

Data Index: 6635881 (Open Web Text)

Max Activating Token Index: 987

Text #19

Max Range: 3.5706. Min Range: -3.5706

Max Act: 3.3850. Min Act: -0.1700

Data Index: 2558798 (Open Web Text)

Max Activating Token Index: 31