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

Dataset: Open Web Text

Neuron 1090 in Layer 5

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: 4.7468. Min Range: -4.7468

Max Act: 4.7468. Min Act: -0.1700

Data Index: 5162689 (Open Web Text)

Max Activating Token Index: 781

Text #1

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.6272. Min Act: -0.1700

Data Index: 6451404 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.6305. Min Act: -0.1700

Data Index: 6292112 (Open Web Text)

Max Activating Token Index: 513

Text #3

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.5369. Min Act: -0.1700

Data Index: 1583763 (Open Web Text)

Max Activating Token Index: 471

Text #4

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.5310. Min Act: -0.1700

Data Index: 3240413 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.4821. Min Act: -0.1700

Data Index: 2014861 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.4673. Min Act: -0.1700

Data Index: 1391749 (Open Web Text)

Max Activating Token Index: 662

Text #7

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.4197. Min Act: -0.1700

Data Index: 8006547 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.4014. Min Act: -0.1700

Data Index: 8744637 (Open Web Text)

Max Activating Token Index: 870

Text #9

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3785. Min Act: -0.1700

Data Index: 6839434 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3653. Min Act: -0.1700

Data Index: 5277765 (Open Web Text)

Max Activating Token Index: 763

Text #11

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.4086. Min Act: -0.1700

Data Index: 4664229 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3522. Min Act: -0.1700

Data Index: 1761392 (Open Web Text)

Max Activating Token Index: 825

Text #13

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3585. Min Act: -0.1700

Data Index: 8807451 (Open Web Text)

Max Activating Token Index: 486

Text #14

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3553. Min Act: -0.1700

Data Index: 4690013 (Open Web Text)

Max Activating Token Index: 684

Text #15

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3518. Min Act: -0.1700

Data Index: 3175572 (Open Web Text)

Max Activating Token Index: 636

Text #16

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3109. Min Act: -0.1700

Data Index: 1073650 (Open Web Text)

Max Activating Token Index: 330

Text #17

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3232. Min Act: -0.1700

Data Index: 1369578 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.3127. Min Act: -0.1700

Data Index: 7964438 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 4.7468. Min Range: -4.7468

Max Act: 4.2929. Min Act: -0.1700

Data Index: 5491459 (Open Web Text)

Max Activating Token Index: 941