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

Dataset: Open Web Text

Neuron 2825 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: 3.3568. Min Range: -3.3568

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1452429 (Open Web Text)

Max Activating Token Index: 443

Text #1

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.3307. Min Act: -0.1700

Data Index: 755319 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.3280. Min Act: -0.1700

Data Index: 7388614 (Open Web Text)

Max Activating Token Index: 514

Text #3

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.3196. Min Act: -0.1700

Data Index: 2732551 (Open Web Text)

Max Activating Token Index: 58

Text #4

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.3420. Min Act: -0.1700

Data Index: 4059526 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2676. Min Act: -0.1700

Data Index: 2493075 (Open Web Text)

Max Activating Token Index: 425

Text #6

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1844. Min Act: -0.1700

Data Index: 7495619 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2149. Min Act: -0.1700

Data Index: 1521994 (Open Web Text)

Max Activating Token Index: 727

Text #8

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2250. Min Act: -0.1700

Data Index: 6846937 (Open Web Text)

Max Activating Token Index: 137

Text #9

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2135. Min Act: -0.1700

Data Index: 6903723 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2216. Min Act: -0.1700

Data Index: 3192439 (Open Web Text)

Max Activating Token Index: 731

Text #11

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2076. Min Act: -0.1700

Data Index: 8080673 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2125. Min Act: -0.1700

Data Index: 7276983 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2016. Min Act: -0.1700

Data Index: 2542027 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1579. Min Act: -0.1700

Data Index: 3438606 (Open Web Text)

Max Activating Token Index: 214

Text #15

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2035. Min Act: -0.1700

Data Index: 8418446 (Open Web Text)

Max Activating Token Index: 379

Text #16

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1905. Min Act: -0.1700

Data Index: 6961451 (Open Web Text)

Max Activating Token Index: 644

Text #17

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1767. Min Act: -0.1700

Data Index: 4564152 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.2091. Min Act: -0.1700

Data Index: 7534650 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 3.3568. Min Range: -3.3568

Max Act: 3.1927. Min Act: -0.1700

Data Index: 4596178 (Open Web Text)

Max Activating Token Index: 80