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

Dataset: Open Web Text

Neuron 1018 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: 3.3491. Min Range: -3.3491

Max Act: 3.3491. Min Act: -0.1700

Data Index: 605804 (Open Web Text)

Max Activating Token Index: 940

Text #1

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2276. Min Act: -0.1700

Data Index: 6003558 (Open Web Text)

Max Activating Token Index: 746

Text #2

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2632. Min Act: -0.1700

Data Index: 2074181 (Open Web Text)

Max Activating Token Index: 584

Text #3

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2526. Min Act: -0.1700

Data Index: 1407724 (Open Web Text)

Max Activating Token Index: 1001

Text #4

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2381. Min Act: -0.1700

Data Index: 6391237 (Open Web Text)

Max Activating Token Index: 946

Text #5

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2315. Min Act: -0.1700

Data Index: 3070556 (Open Web Text)

Max Activating Token Index: 684

Text #6

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1988. Min Act: -0.1700

Data Index: 2358349 (Open Web Text)

Max Activating Token Index: 328

Text #7

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1976. Min Act: -0.1700

Data Index: 3725243 (Open Web Text)

Max Activating Token Index: 303

Text #8

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1731. Min Act: -0.1700

Data Index: 3981623 (Open Web Text)

Max Activating Token Index: 522

Text #9

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2027. Min Act: -0.1700

Data Index: 5910895 (Open Web Text)

Max Activating Token Index: 855

Text #10

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1773. Min Act: -0.1700

Data Index: 2754311 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1686. Min Act: -0.1700

Data Index: 8478680 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1857. Min Act: -0.1700

Data Index: 5805528 (Open Web Text)

Max Activating Token Index: 118

Text #13

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1759. Min Act: -0.1700

Data Index: 1454040 (Open Web Text)

Max Activating Token Index: 861

Text #14

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1809. Min Act: -0.1700

Data Index: 6732177 (Open Web Text)

Max Activating Token Index: 136

Text #15

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1581. Min Act: -0.1700

Data Index: 4466064 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1909. Min Act: -0.1700

Data Index: 8135857 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1686. Min Act: -0.1700

Data Index: 4376376 (Open Web Text)

Max Activating Token Index: 335

Text #18

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1240. Min Act: -0.1700

Data Index: 334343 (Open Web Text)

Max Activating Token Index: 687

Text #19

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1503. Min Act: -0.1700

Data Index: 2666032 (Open Web Text)

Max Activating Token Index: 818