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

Dataset: Open Web Text

Neuron 2759 in Layer 4

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: 3.3926. Min Range: -3.3926

Max Act: 3.3926. Min Act: -0.1700

Data Index: 7211760 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.2507. Min Act: -0.1700

Data Index: 3213866 (Open Web Text)

Max Activating Token Index: 950

Text #2

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.2662. Min Act: -0.1700

Data Index: 6952489 (Open Web Text)

Max Activating Token Index: 546

Text #3

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.2418. Min Act: -0.1700

Data Index: 6203471 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.2044. Min Act: -0.1700

Data Index: 1152924 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.2003. Min Act: -0.1700

Data Index: 2292373 (Open Web Text)

Max Activating Token Index: 297

Text #6

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1842. Min Act: -0.1700

Data Index: 6980488 (Open Web Text)

Max Activating Token Index: 804

Text #7

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1380. Min Act: -0.1700

Data Index: 8771861 (Open Web Text)

Max Activating Token Index: 170

Text #8

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1656. Min Act: -0.1700

Data Index: 6074193 (Open Web Text)

Max Activating Token Index: 489

Text #9

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1667. Min Act: -0.1700

Data Index: 7581732 (Open Web Text)

Max Activating Token Index: 299

Text #10

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1736. Min Act: -0.1700

Data Index: 6421890 (Open Web Text)

Max Activating Token Index: 566

Text #11

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1474. Min Act: -0.1700

Data Index: 1702408 (Open Web Text)

Max Activating Token Index: 870

Text #12

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1680. Min Act: -0.1700

Data Index: 5464285 (Open Web Text)

Max Activating Token Index: 144

Text #13

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1577. Min Act: -0.1700

Data Index: 6215268 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1508. Min Act: -0.1700

Data Index: 578276 (Open Web Text)

Max Activating Token Index: 325

Text #15

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1563. Min Act: -0.1700

Data Index: 3734569 (Open Web Text)

Max Activating Token Index: 872

Text #16

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1613. Min Act: -0.1700

Data Index: 6752863 (Open Web Text)

Max Activating Token Index: 733

Text #17

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1601. Min Act: -0.1700

Data Index: 8697337 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1216. Min Act: -0.1700

Data Index: 4904446 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 3.3926. Min Range: -3.3926

Max Act: 3.1085. Min Act: -0.1700

Data Index: 184224 (Open Web Text)

Max Activating Token Index: 984