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

Dataset: Open Web Text

Neuron 583 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: 4.6886. Min Range: -4.6886

Max Act: 4.6886. Min Act: -0.1700

Data Index: 1863602 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.6769. Min Act: -0.1700

Data Index: 6330016 (Open Web Text)

Max Activating Token Index: 483

Text #2

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.6581. Min Act: -0.1700

Data Index: 6007101 (Open Web Text)

Max Activating Token Index: 787

Text #3

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.6211. Min Act: -0.1700

Data Index: 4156508 (Open Web Text)

Max Activating Token Index: 554

Text #4

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.6359. Min Act: -0.1700

Data Index: 4969072 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5947. Min Act: -0.1700

Data Index: 5120574 (Open Web Text)

Max Activating Token Index: 403

Text #6

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.6150. Min Act: -0.1700

Data Index: 1257265 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.6239. Min Act: -0.1700

Data Index: 235859 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.6066. Min Act: -0.1700

Data Index: 1643635 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5885. Min Act: -0.1700

Data Index: 2516541 (Open Web Text)

Max Activating Token Index: 607

Text #10

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5925. Min Act: -0.1700

Data Index: 3456550 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5904. Min Act: -0.1700

Data Index: 6038184 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5875. Min Act: -0.1700

Data Index: 6013208 (Open Web Text)

Max Activating Token Index: 660

Text #13

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5911. Min Act: -0.1700

Data Index: 2797922 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5812. Min Act: -0.1700

Data Index: 5360996 (Open Web Text)

Max Activating Token Index: 662

Text #15

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5718. Min Act: -0.1700

Data Index: 5157572 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5890. Min Act: -0.1700

Data Index: 420494 (Open Web Text)

Max Activating Token Index: 737

Text #17

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5809. Min Act: -0.1700

Data Index: 4848757 (Open Web Text)

Max Activating Token Index: 604

Text #18

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5833. Min Act: -0.1700

Data Index: 4076919 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 4.6886. Min Range: -4.6886

Max Act: 4.5852. Min Act: -0.1700

Data Index: 829303 (Open Web Text)

Max Activating Token Index: 599