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

Dataset: Open Web Text

Neuron 2847 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: 4.2855. Min Range: -4.2855

Max Act: 4.2855. Min Act: -0.1700

Data Index: 6033417 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.2198. Min Act: -0.1700

Data Index: 6905832 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1902. Min Act: -0.1700

Data Index: 795513 (Open Web Text)

Max Activating Token Index: 389

Text #3

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1764. Min Act: -0.1700

Data Index: 5993314 (Open Web Text)

Max Activating Token Index: 604

Text #4

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1563. Min Act: -0.1700

Data Index: 2175065 (Open Web Text)

Max Activating Token Index: 807

Text #5

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1712. Min Act: -0.1700

Data Index: 8247408 (Open Web Text)

Max Activating Token Index: 320

Text #6

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1729. Min Act: -0.1700

Data Index: 3574863 (Open Web Text)

Max Activating Token Index: 979

Text #7

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1322. Min Act: -0.1700

Data Index: 7007693 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1547. Min Act: -0.1700

Data Index: 8030914 (Open Web Text)

Max Activating Token Index: 312

Text #9

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1245. Min Act: -0.1700

Data Index: 2551562 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1127. Min Act: -0.1700

Data Index: 8806475 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1164. Min Act: -0.1700

Data Index: 1037864 (Open Web Text)

Max Activating Token Index: 166

Text #12

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.0981. Min Act: -0.1700

Data Index: 5405672 (Open Web Text)

Max Activating Token Index: 601

Text #13

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1041. Min Act: -0.1700

Data Index: 1133216 (Open Web Text)

Max Activating Token Index: 606

Text #14

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.0915. Min Act: -0.1700

Data Index: 3943989 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.0927. Min Act: -0.1700

Data Index: 8662684 (Open Web Text)

Max Activating Token Index: 808

Text #16

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.1074. Min Act: -0.1700

Data Index: 2912325 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.0591. Min Act: -0.1700

Data Index: 5328100 (Open Web Text)

Max Activating Token Index: 85

Text #18

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.0993. Min Act: -0.1700

Data Index: 53474 (Open Web Text)

Max Activating Token Index: 769

Text #19

Max Range: 4.2855. Min Range: -4.2855

Max Act: 4.0688. Min Act: -0.1700

Data Index: 6919557 (Open Web Text)

Max Activating Token Index: 554