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

Dataset: Open Web Text

Neuron 1006 in Layer 6

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: 4.1733. Min Range: -4.1733

Max Act: 4.1733. Min Act: -0.1700

Data Index: 1383876 (Open Web Text)

Max Activating Token Index: 411

Text #1

Max Range: 4.1733. Min Range: -4.1733

Max Act: 4.1007. Min Act: -0.1700

Data Index: 2874558 (Open Web Text)

Max Activating Token Index: 677

Text #2

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9959. Min Act: -0.1700

Data Index: 2552913 (Open Web Text)

Max Activating Token Index: 511

Text #3

Max Range: 4.1733. Min Range: -4.1733

Max Act: 4.0345. Min Act: -0.1700

Data Index: 5419414 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 4.1733. Min Range: -4.1733

Max Act: 4.0016. Min Act: -0.1700

Data Index: 3817818 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 4.1733. Min Range: -4.1733

Max Act: 4.0356. Min Act: -0.1700

Data Index: 5419415 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9635. Min Act: -0.1700

Data Index: 7700947 (Open Web Text)

Max Activating Token Index: 705

Text #7

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9679. Min Act: -0.1700

Data Index: 7194302 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9668. Min Act: -0.1700

Data Index: 8315371 (Open Web Text)

Max Activating Token Index: 64

Text #9

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9513. Min Act: -0.1700

Data Index: 3973923 (Open Web Text)

Max Activating Token Index: 169

Text #10

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9248. Min Act: -0.1700

Data Index: 2066347 (Open Web Text)

Max Activating Token Index: 987

Text #11

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9568. Min Act: -0.1700

Data Index: 5880224 (Open Web Text)

Max Activating Token Index: 277

Text #12

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9412. Min Act: -0.1700

Data Index: 8708660 (Open Web Text)

Max Activating Token Index: 281

Text #13

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9488. Min Act: -0.1700

Data Index: 2103243 (Open Web Text)

Max Activating Token Index: 234

Text #14

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9345. Min Act: -0.1700

Data Index: 642060 (Open Web Text)

Max Activating Token Index: 573

Text #15

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9565. Min Act: -0.1700

Data Index: 3749429 (Open Web Text)

Max Activating Token Index: 850

Text #16

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9830. Min Act: -0.1700

Data Index: 2564233 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9614. Min Act: -0.1700

Data Index: 3391902 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9423. Min Act: -0.1700

Data Index: 5967495 (Open Web Text)

Max Activating Token Index: 296

Text #19

Max Range: 4.1733. Min Range: -4.1733

Max Act: 3.9259. Min Act: -0.1700

Data Index: 2804489 (Open Web Text)

Max Activating Token Index: 312