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

Dataset: Open Web Text

Neuron 1942 in Layer 3

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: 5.2475. Min Range: -5.2475

Max Act: 5.2475. Min Act: -0.1700

Data Index: 3180141 (Open Web Text)

Max Activating Token Index: 734

Text #1

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.2459. Min Act: -0.1700

Data Index: 3643349 (Open Web Text)

Max Activating Token Index: 734

Text #2

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.2134. Min Act: -0.1700

Data Index: 3567751 (Open Web Text)

Max Activating Token Index: 573

Text #3

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.2108. Min Act: -0.1700

Data Index: 293177 (Open Web Text)

Max Activating Token Index: 277

Text #4

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1906. Min Act: -0.1700

Data Index: 8166980 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1820. Min Act: -0.1700

Data Index: 617758 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1927. Min Act: -0.1700

Data Index: 5707960 (Open Web Text)

Max Activating Token Index: 781

Text #7

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1745. Min Act: -0.1700

Data Index: 5256839 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1651. Min Act: -0.1700

Data Index: 4243325 (Open Web Text)

Max Activating Token Index: 129

Text #9

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1579. Min Act: -0.1700

Data Index: 91522 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1889. Min Act: -0.1700

Data Index: 4883738 (Open Web Text)

Max Activating Token Index: 861

Text #11

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.2046. Min Act: -0.1700

Data Index: 2086932 (Open Web Text)

Max Activating Token Index: 578

Text #12

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1826. Min Act: -0.1700

Data Index: 8215046 (Open Web Text)

Max Activating Token Index: 972

Text #13

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1702. Min Act: -0.1700

Data Index: 4697165 (Open Web Text)

Max Activating Token Index: 59

Text #14

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1695. Min Act: -0.1700

Data Index: 1839670 (Open Web Text)

Max Activating Token Index: 360

Text #15

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1808. Min Act: -0.1700

Data Index: 3415997 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1518. Min Act: -0.1700

Data Index: 7931207 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1649. Min Act: -0.1700

Data Index: 2934188 (Open Web Text)

Max Activating Token Index: 657

Text #18

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1485. Min Act: -0.1700

Data Index: 5433430 (Open Web Text)

Max Activating Token Index: 731

Text #19

Max Range: 5.2475. Min Range: -5.2475

Max Act: 5.1543. Min Act: -0.1700

Data Index: 1781904 (Open Web Text)

Max Activating Token Index: 382