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

Dataset: Open Web Text

Neuron 537 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: 2.6232. Min Range: -2.6232

Max Act: 2.5412. Min Act: -0.1700

Data Index: 3238429 (Open Web Text)

Max Activating Token Index: 354

Text #1

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.6232. Min Act: -0.1700

Data Index: 6817773 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.5522. Min Act: -0.1700

Data Index: 5450605 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.4151. Min Act: -0.1700

Data Index: 4206765 (Open Web Text)

Max Activating Token Index: 1007

Text #4

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.3963. Min Act: -0.1700

Data Index: 1604289 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.3809. Min Act: -0.1700

Data Index: 1866363 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.2967. Min Act: -0.1700

Data Index: 2667615 (Open Web Text)

Max Activating Token Index: 762

Text #7

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.4275. Min Act: -0.1700

Data Index: 5487776 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.3431. Min Act: -0.1700

Data Index: 7645873 (Open Web Text)

Max Activating Token Index: 785

Text #9

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.3270. Min Act: -0.1700

Data Index: 7077752 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.3567. Min Act: -0.1700

Data Index: 3598121 (Open Web Text)

Max Activating Token Index: 888

Text #11

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.2561. Min Act: -0.1700

Data Index: 8355607 (Open Web Text)

Max Activating Token Index: 954

Text #12

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.2625. Min Act: -0.1700

Data Index: 3109758 (Open Web Text)

Max Activating Token Index: 954

Text #13

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.3427. Min Act: -0.1700

Data Index: 3134979 (Open Web Text)

Max Activating Token Index: 603

Text #14

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.2684. Min Act: -0.1700

Data Index: 7213485 (Open Web Text)

Max Activating Token Index: 469

Text #15

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.2849. Min Act: -0.1700

Data Index: 5097540 (Open Web Text)

Max Activating Token Index: 412

Text #16

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.3984. Min Act: -0.1700

Data Index: 3085618 (Open Web Text)

Max Activating Token Index: 412

Text #17

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.2674. Min Act: -0.1700

Data Index: 861182 (Open Web Text)

Max Activating Token Index: 264

Text #18

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.3076. Min Act: -0.1700

Data Index: 1172423 (Open Web Text)

Max Activating Token Index: 688

Text #19

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.2741. Min Act: -0.1700

Data Index: 5607373 (Open Web Text)

Max Activating Token Index: 602