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

Dataset: Open Web Text

Neuron 1100 in Layer 4

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: 1.2709. Min Range: -1.2709

Max Act: 1.2709. Min Act: -0.1700

Data Index: 6213991 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.2309. Min Act: -0.1700

Data Index: 6175741 (Open Web Text)

Max Activating Token Index: 734

Text #2

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.2150. Min Act: -0.1700

Data Index: 6220450 (Open Web Text)

Max Activating Token Index: 472

Text #3

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.2079. Min Act: -0.1700

Data Index: 2459141 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1623. Min Act: -0.1700

Data Index: 900703 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1594. Min Act: -0.1700

Data Index: 6800197 (Open Web Text)

Max Activating Token Index: 914

Text #6

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1731. Min Act: -0.1700

Data Index: 7669107 (Open Web Text)

Max Activating Token Index: 751

Text #7

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1690. Min Act: -0.1700

Data Index: 6109109 (Open Web Text)

Max Activating Token Index: 637

Text #8

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1590. Min Act: -0.1700

Data Index: 945344 (Open Web Text)

Max Activating Token Index: 630

Text #9

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1614. Min Act: -0.1700

Data Index: 2854985 (Open Web Text)

Max Activating Token Index: 608

Text #10

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1396. Min Act: -0.1700

Data Index: 5809766 (Open Web Text)

Max Activating Token Index: 575

Text #11

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1429. Min Act: -0.1700

Data Index: 6270043 (Open Web Text)

Max Activating Token Index: 806

Text #12

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1331. Min Act: -0.1700

Data Index: 4033785 (Open Web Text)

Max Activating Token Index: 214

Text #13

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1380. Min Act: -0.1700

Data Index: 7456116 (Open Web Text)

Max Activating Token Index: 545

Text #14

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1281. Min Act: -0.1700

Data Index: 1743948 (Open Web Text)

Max Activating Token Index: 555

Text #15

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1215. Min Act: -0.1700

Data Index: 6706327 (Open Web Text)

Max Activating Token Index: 362

Text #16

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1202. Min Act: -0.1700

Data Index: 6609243 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1121. Min Act: -0.1700

Data Index: 308184 (Open Web Text)

Max Activating Token Index: 615

Text #18

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1026. Min Act: -0.1700

Data Index: 6796040 (Open Web Text)

Max Activating Token Index: 825

Text #19

Max Range: 1.2709. Min Range: -1.2709

Max Act: 1.1067. Min Act: -0.1700

Data Index: 5555367 (Open Web Text)

Max Activating Token Index: 996