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

Dataset: Open Web Text

Neuron 2530 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: 7.6012. Min Range: -7.6012

Max Act: 7.6012. Min Act: -0.1700

Data Index: 1279308 (Open Web Text)

Max Activating Token Index: 475

Text #1

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.5033. Min Act: -0.1700

Data Index: 5193158 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.5106. Min Act: -0.1700

Data Index: 6047449 (Open Web Text)

Max Activating Token Index: 604

Text #3

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.5072. Min Act: -0.1700

Data Index: 5901118 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.4560. Min Act: -0.1700

Data Index: 2537629 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.4188. Min Act: -0.1700

Data Index: 4809718 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.3521. Min Act: -0.1700

Data Index: 7995788 (Open Web Text)

Max Activating Token Index: 527

Text #7

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.3050. Min Act: -0.1700

Data Index: 2658719 (Open Web Text)

Max Activating Token Index: 875

Text #8

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.3335. Min Act: -0.1700

Data Index: 265196 (Open Web Text)

Max Activating Token Index: 683

Text #9

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.2570. Min Act: -0.1700

Data Index: 3370794 (Open Web Text)

Max Activating Token Index: 868

Text #10

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.1092. Min Act: -0.1700

Data Index: 2437223 (Open Web Text)

Max Activating Token Index: 703

Text #11

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.2122. Min Act: -0.1700

Data Index: 1670479 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.1158. Min Act: -0.1700

Data Index: 1324599 (Open Web Text)

Max Activating Token Index: 176

Text #13

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.0679. Min Act: -0.1700

Data Index: 5895154 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.0764. Min Act: -0.1700

Data Index: 50060 (Open Web Text)

Max Activating Token Index: 682

Text #15

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.0246. Min Act: -0.1700

Data Index: 6282558 (Open Web Text)

Max Activating Token Index: 781

Text #16

Max Range: 7.6012. Min Range: -7.6012

Max Act: 6.9144. Min Act: -0.1700

Data Index: 3808070 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 7.6012. Min Range: -7.6012

Max Act: 7.0022. Min Act: -0.1700

Data Index: 7057905 (Open Web Text)

Max Activating Token Index: 493

Text #18

Max Range: 7.6012. Min Range: -7.6012

Max Act: 6.9819. Min Act: -0.1700

Data Index: 5783918 (Open Web Text)

Max Activating Token Index: 708

Text #19

Max Range: 7.6012. Min Range: -7.6012

Max Act: 6.9368. Min Act: -0.1700

Data Index: 1933026 (Open Web Text)

Max Activating Token Index: 398