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

Dataset: Open Web Text

Neuron 1484 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: 4.4731. Min Range: -4.4731

Max Act: 4.4731. Min Act: -0.1700

Data Index: 3335446 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.2984. Min Act: -0.1700

Data Index: 4596014 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.2910. Min Act: -0.1700

Data Index: 670388 (Open Web Text)

Max Activating Token Index: 920

Text #3

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.2856. Min Act: -0.1700

Data Index: 5695872 (Open Web Text)

Max Activating Token Index: 475

Text #4

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.2356. Min Act: -0.1700

Data Index: 6741207 (Open Web Text)

Max Activating Token Index: 890

Text #5

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.2201. Min Act: -0.1700

Data Index: 3699597 (Open Web Text)

Max Activating Token Index: 283

Text #6

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1826. Min Act: -0.1700

Data Index: 7152133 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.2229. Min Act: -0.1700

Data Index: 2140384 (Open Web Text)

Max Activating Token Index: 808

Text #8

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1705. Min Act: -0.1700

Data Index: 4782308 (Open Web Text)

Max Activating Token Index: 882

Text #9

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1678. Min Act: -0.1700

Data Index: 694337 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1306. Min Act: -0.1700

Data Index: 2865976 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1368. Min Act: -0.1700

Data Index: 8170453 (Open Web Text)

Max Activating Token Index: 444

Text #12

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1188. Min Act: -0.1700

Data Index: 984662 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1353. Min Act: -0.1700

Data Index: 723598 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.0863. Min Act: -0.1700

Data Index: 2633648 (Open Web Text)

Max Activating Token Index: 247

Text #15

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.0901. Min Act: -0.1700

Data Index: 4538828 (Open Web Text)

Max Activating Token Index: 667

Text #16

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1577. Min Act: -0.1700

Data Index: 6093071 (Open Web Text)

Max Activating Token Index: 557

Text #17

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.1271. Min Act: -0.1700

Data Index: 8201822 (Open Web Text)

Max Activating Token Index: 989

Text #18

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.0691. Min Act: -0.1700

Data Index: 4544609 (Open Web Text)

Max Activating Token Index: 526

Text #19

Max Range: 4.4731. Min Range: -4.4731

Max Act: 4.0783. Min Act: -0.1700

Data Index: 1508198 (Open Web Text)

Max Activating Token Index: 444