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

Dataset: Open Web Text

Neuron 1907 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: 3.5424. Min Range: -3.5424

Max Act: 3.5424. Min Act: -0.1700

Data Index: 6240620 (Open Web Text)

Max Activating Token Index: 77

Text #1

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.5041. Min Act: -0.1700

Data Index: 8288776 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.3918. Min Act: -0.1700

Data Index: 6182590 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.3703. Min Act: -0.1700

Data Index: 5494040 (Open Web Text)

Max Activating Token Index: 667

Text #4

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.3774. Min Act: -0.1700

Data Index: 1483621 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.3102. Min Act: -0.1700

Data Index: 8700885 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2926. Min Act: -0.1700

Data Index: 6182591 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.3173. Min Act: -0.1700

Data Index: 5494041 (Open Web Text)

Max Activating Token Index: 538

Text #8

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2827. Min Act: -0.1700

Data Index: 5213395 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2919. Min Act: -0.1700

Data Index: 4774147 (Open Web Text)

Max Activating Token Index: 150

Text #10

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2709. Min Act: -0.1700

Data Index: 4774144 (Open Web Text)

Max Activating Token Index: 137

Text #11

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2544. Min Act: -0.1700

Data Index: 7535454 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2528. Min Act: -0.1700

Data Index: 5855576 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2641. Min Act: -0.1700

Data Index: 6182598 (Open Web Text)

Max Activating Token Index: 845

Text #14

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2495. Min Act: -0.1700

Data Index: 5494045 (Open Web Text)

Max Activating Token Index: 469

Text #15

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2472. Min Act: -0.1700

Data Index: 6263252 (Open Web Text)

Max Activating Token Index: 666

Text #16

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2303. Min Act: -0.1700

Data Index: 1358872 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2289. Min Act: -0.1700

Data Index: 6051046 (Open Web Text)

Max Activating Token Index: 889

Text #18

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2215. Min Act: -0.1700

Data Index: 7745337 (Open Web Text)

Max Activating Token Index: 427

Text #19

Max Range: 3.5424. Min Range: -3.5424

Max Act: 3.2269. Min Act: -0.1700

Data Index: 3752951 (Open Web Text)

Max Activating Token Index: 678