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

Dataset: Open Web Text

Neuron 2223 in Layer 4

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: 3.6196. Min Range: -3.6196

Max Act: 3.6196. Min Act: -0.1700

Data Index: 6623553 (Open Web Text)

Max Activating Token Index: 898

Text #1

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5864. Min Act: -0.1700

Data Index: 522193 (Open Web Text)

Max Activating Token Index: 38

Text #2

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.6149. Min Act: -0.1700

Data Index: 3804284 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.6030. Min Act: -0.1700

Data Index: 6716278 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5997. Min Act: -0.1700

Data Index: 4088820 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5886. Min Act: -0.1700

Data Index: 7619832 (Open Web Text)

Max Activating Token Index: 945

Text #6

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5949. Min Act: -0.1700

Data Index: 1192237 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5867. Min Act: -0.1700

Data Index: 3804285 (Open Web Text)

Max Activating Token Index: 120

Text #8

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5920. Min Act: -0.1700

Data Index: 7209366 (Open Web Text)

Max Activating Token Index: 452

Text #9

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5736. Min Act: -0.1700

Data Index: 7217755 (Open Web Text)

Max Activating Token Index: 118

Text #10

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5728. Min Act: -0.1700

Data Index: 835806 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5778. Min Act: -0.1700

Data Index: 7217754 (Open Web Text)

Max Activating Token Index: 1012

Text #12

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5477. Min Act: -0.1700

Data Index: 3802667 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5276. Min Act: -0.1700

Data Index: 4477336 (Open Web Text)

Max Activating Token Index: 411

Text #14

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5345. Min Act: -0.1700

Data Index: 4618193 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5225. Min Act: -0.1700

Data Index: 6715294 (Open Web Text)

Max Activating Token Index: 507

Text #16

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5199. Min Act: -0.1700

Data Index: 3428283 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5265. Min Act: -0.1700

Data Index: 2293163 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5380. Min Act: -0.1700

Data Index: 2300241 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 3.6196. Min Range: -3.6196

Max Act: 3.5088. Min Act: -0.1700

Data Index: 7658321 (Open Web Text)

Max Activating Token Index: 349