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

Dataset: Open Web Text

Neuron 2647 in Layer 1

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: 3.7841. Min Range: -3.7841

Max Act: 3.7643. Min Act: -0.1700

Data Index: 495326 (Open Web Text)

Max Activating Token Index: 361

Text #1

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7841. Min Act: -0.1700

Data Index: 8339703 (Open Web Text)

Max Activating Token Index: 214

Text #2

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6837. Min Act: -0.1700

Data Index: 1941583 (Open Web Text)

Max Activating Token Index: 334

Text #3

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6997. Min Act: -0.1700

Data Index: 7688029 (Open Web Text)

Max Activating Token Index: 399

Text #4

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6928. Min Act: -0.1700

Data Index: 5049409 (Open Web Text)

Max Activating Token Index: 340

Text #5

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6827. Min Act: -0.1700

Data Index: 2517659 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7039. Min Act: -0.1700

Data Index: 8324663 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6983. Min Act: -0.1700

Data Index: 8222866 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6829. Min Act: -0.1700

Data Index: 4735325 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6734. Min Act: -0.1700

Data Index: 8165206 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6909. Min Act: -0.1700

Data Index: 1772135 (Open Web Text)

Max Activating Token Index: 278

Text #11

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6510. Min Act: -0.1700

Data Index: 2593216 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6564. Min Act: -0.1700

Data Index: 3139502 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6515. Min Act: -0.1700

Data Index: 3421658 (Open Web Text)

Max Activating Token Index: 356

Text #14

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6630. Min Act: -0.1700

Data Index: 3800054 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6416. Min Act: -0.1700

Data Index: 874605 (Open Web Text)

Max Activating Token Index: 528

Text #16

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6704. Min Act: -0.1700

Data Index: 3869524 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6450. Min Act: -0.1700

Data Index: 5914291 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6426. Min Act: -0.1700

Data Index: 6837027 (Open Web Text)

Max Activating Token Index: 300

Text #19

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6667. Min Act: -0.1700

Data Index: 7476742 (Open Web Text)

Max Activating Token Index: 4