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

Dataset: Open Web Text

Neuron 2579 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: 3.5628. Min Range: -3.5628

Max Act: 3.5628. Min Act: -0.1700

Data Index: 2171498 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.3844. Min Act: -0.1700

Data Index: 4347447 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.3290. Min Act: -0.1700

Data Index: 4152306 (Open Web Text)

Max Activating Token Index: 866

Text #3

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2976. Min Act: -0.1700

Data Index: 2190557 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2709. Min Act: -0.1700

Data Index: 6194643 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2841. Min Act: -0.1700

Data Index: 675823 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2455. Min Act: -0.1700

Data Index: 2598031 (Open Web Text)

Max Activating Token Index: 183

Text #7

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2718. Min Act: -0.1700

Data Index: 1580638 (Open Web Text)

Max Activating Token Index: 1003

Text #8

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2432. Min Act: -0.1700

Data Index: 2596033 (Open Web Text)

Max Activating Token Index: 152

Text #9

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2251. Min Act: -0.1700

Data Index: 5896139 (Open Web Text)

Max Activating Token Index: 850

Text #10

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2065. Min Act: -0.1700

Data Index: 2876940 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2466. Min Act: -0.1700

Data Index: 7548657 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2403. Min Act: -0.1700

Data Index: 8634597 (Open Web Text)

Max Activating Token Index: 51

Text #13

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2432. Min Act: -0.1700

Data Index: 8772620 (Open Web Text)

Max Activating Token Index: 451

Text #14

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.3068. Min Act: -0.1700

Data Index: 1226299 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2328. Min Act: -0.1700

Data Index: 5040003 (Open Web Text)

Max Activating Token Index: 792

Text #16

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2145. Min Act: -0.1700

Data Index: 5656137 (Open Web Text)

Max Activating Token Index: 127

Text #17

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2002. Min Act: -0.1700

Data Index: 1261670 (Open Web Text)

Max Activating Token Index: 408

Text #18

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.2292. Min Act: -0.1700

Data Index: 6696565 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 3.5628. Min Range: -3.5628

Max Act: 3.1978. Min Act: -0.1700

Data Index: 4495695 (Open Web Text)

Max Activating Token Index: 222