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

Dataset: Open Web Text

Neuron 786 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: 4.0959. Min Range: -4.0959

Max Act: 4.0959. Min Act: -0.1700

Data Index: 4849039 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 4.0959. Min Range: -4.0959

Max Act: 4.0764. Min Act: -0.1700

Data Index: 2836569 (Open Web Text)

Max Activating Token Index: 351

Text #2

Max Range: 4.0959. Min Range: -4.0959

Max Act: 4.0414. Min Act: -0.1700

Data Index: 1615179 (Open Web Text)

Max Activating Token Index: 75

Text #3

Max Range: 4.0959. Min Range: -4.0959

Max Act: 4.0254. Min Act: -0.1700

Data Index: 4611972 (Open Web Text)

Max Activating Token Index: 111

Text #4

Max Range: 4.0959. Min Range: -4.0959

Max Act: 4.0413. Min Act: -0.1700

Data Index: 5568941 (Open Web Text)

Max Activating Token Index: 973

Text #5

Max Range: 4.0959. Min Range: -4.0959

Max Act: 4.0174. Min Act: -0.1700

Data Index: 2257953 (Open Web Text)

Max Activating Token Index: 784

Text #6

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.9400. Min Act: -0.1700

Data Index: 6008401 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.9793. Min Act: -0.1700

Data Index: 3220193 (Open Web Text)

Max Activating Token Index: 574

Text #8

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.9752. Min Act: -0.1700

Data Index: 3735052 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8516. Min Act: -0.1700

Data Index: 3358144 (Open Web Text)

Max Activating Token Index: 449

Text #10

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8594. Min Act: -0.1700

Data Index: 7673259 (Open Web Text)

Max Activating Token Index: 877

Text #11

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8737. Min Act: -0.1700

Data Index: 3669010 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8651. Min Act: -0.1700

Data Index: 7459725 (Open Web Text)

Max Activating Token Index: 618

Text #13

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8321. Min Act: -0.1700

Data Index: 1458201 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8351. Min Act: -0.1700

Data Index: 7406876 (Open Web Text)

Max Activating Token Index: 641

Text #15

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8123. Min Act: -0.1700

Data Index: 1178721 (Open Web Text)

Max Activating Token Index: 24

Text #16

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8104. Min Act: -0.1700

Data Index: 5665245 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.8115. Min Act: -0.1700

Data Index: 7268867 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.7744. Min Act: -0.1700

Data Index: 7416044 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.0959. Min Range: -4.0959

Max Act: 3.7543. Min Act: -0.1700

Data Index: 3444476 (Open Web Text)

Max Activating Token Index: 810