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

Dataset: Open Web Text

Neuron 860 in Layer 6

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: 4.5589. Min Range: -4.5589

Max Act: 4.5589. Min Act: -0.1700

Data Index: 697060 (Open Web Text)

Max Activating Token Index: 577

Text #1

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.5557. Min Act: -0.1700

Data Index: 5561790 (Open Web Text)

Max Activating Token Index: 158

Text #2

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.5411. Min Act: -0.1700

Data Index: 7539770 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4994. Min Act: -0.1700

Data Index: 8475883 (Open Web Text)

Max Activating Token Index: 657

Text #4

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4803. Min Act: -0.1700

Data Index: 803032 (Open Web Text)

Max Activating Token Index: 400

Text #5

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.5034. Min Act: -0.1700

Data Index: 2355180 (Open Web Text)

Max Activating Token Index: 248

Text #6

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4480. Min Act: -0.1700

Data Index: 6597800 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4755. Min Act: -0.1700

Data Index: 4680826 (Open Web Text)

Max Activating Token Index: 157

Text #8

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4625. Min Act: -0.1700

Data Index: 1866587 (Open Web Text)

Max Activating Token Index: 664

Text #9

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4426. Min Act: -0.1700

Data Index: 8328022 (Open Web Text)

Max Activating Token Index: 536

Text #10

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4389. Min Act: -0.1700

Data Index: 6375569 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4238. Min Act: -0.1700

Data Index: 7604350 (Open Web Text)

Max Activating Token Index: 106

Text #12

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.3859. Min Act: -0.1700

Data Index: 6570645 (Open Web Text)

Max Activating Token Index: 905

Text #13

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4012. Min Act: -0.1700

Data Index: 273843 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.3952. Min Act: -0.1700

Data Index: 3111083 (Open Web Text)

Max Activating Token Index: 556

Text #15

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.3931. Min Act: -0.1700

Data Index: 1934553 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4157. Min Act: -0.1700

Data Index: 7760680 (Open Web Text)

Max Activating Token Index: 597

Text #17

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4172. Min Act: -0.1700

Data Index: 7909539 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.4018. Min Act: -0.1700

Data Index: 2011121 (Open Web Text)

Max Activating Token Index: 883

Text #19

Max Range: 4.5589. Min Range: -4.5589

Max Act: 4.3860. Min Act: -0.1700

Data Index: 8174466 (Open Web Text)

Max Activating Token Index: 123