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

Dataset: Open Web Text

Neuron 1355 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: 4.2626. Min Range: -4.2626

Max Act: 4.2626. Min Act: -0.1700

Data Index: 1079668 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 4.2626. Min Range: -4.2626

Max Act: 4.0886. Min Act: -0.1700

Data Index: 4212449 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 4.2626. Min Range: -4.2626

Max Act: 4.0894. Min Act: -0.1700

Data Index: 6231070 (Open Web Text)

Max Activating Token Index: 501

Text #3

Max Range: 4.2626. Min Range: -4.2626

Max Act: 4.0178. Min Act: -0.1700

Data Index: 4528170 (Open Web Text)

Max Activating Token Index: 210

Text #4

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9998. Min Act: -0.1700

Data Index: 3023295 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 4.2626. Min Range: -4.2626

Max Act: 4.0022. Min Act: -0.1700

Data Index: 3154008 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9632. Min Act: -0.1700

Data Index: 1845906 (Open Web Text)

Max Activating Token Index: 919

Text #7

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9751. Min Act: -0.1700

Data Index: 2436881 (Open Web Text)

Max Activating Token Index: 224

Text #8

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9732. Min Act: -0.1700

Data Index: 8806720 (Open Web Text)

Max Activating Token Index: 635

Text #9

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9396. Min Act: -0.1700

Data Index: 469579 (Open Web Text)

Max Activating Token Index: 736

Text #10

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9517. Min Act: -0.1700

Data Index: 3167075 (Open Web Text)

Max Activating Token Index: 173

Text #11

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9304. Min Act: -0.1700

Data Index: 376621 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9663. Min Act: -0.1700

Data Index: 4759181 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9322. Min Act: -0.1700

Data Index: 3150055 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9320. Min Act: -0.1700

Data Index: 978103 (Open Web Text)

Max Activating Token Index: 269

Text #15

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9483. Min Act: -0.1700

Data Index: 8105036 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9616. Min Act: -0.1700

Data Index: 7136130 (Open Web Text)

Max Activating Token Index: 153

Text #17

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9287. Min Act: -0.1700

Data Index: 3728631 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9221. Min Act: -0.1700

Data Index: 2690734 (Open Web Text)

Max Activating Token Index: 891

Text #19

Max Range: 4.2626. Min Range: -4.2626

Max Act: 3.9014. Min Act: -0.1700

Data Index: 1422756 (Open Web Text)

Max Activating Token Index: 337