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

Dataset: Open Web Text

Neuron 544 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: 4.7421. Min Range: -4.7421

Max Act: 4.7421. Min Act: -0.1700

Data Index: 6453957 (Open Web Text)

Max Activating Token Index: 521

Text #1

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.5946. Min Act: -0.1700

Data Index: 7914314 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.5245. Min Act: -0.1700

Data Index: 987242 (Open Web Text)

Max Activating Token Index: 201

Text #3

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.5208. Min Act: -0.1700

Data Index: 1567878 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.5379. Min Act: -0.1700

Data Index: 5260629 (Open Web Text)

Max Activating Token Index: 573

Text #5

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.5480. Min Act: -0.1700

Data Index: 696172 (Open Web Text)

Max Activating Token Index: 264

Text #6

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4887. Min Act: -0.1700

Data Index: 8040086 (Open Web Text)

Max Activating Token Index: 759

Text #7

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4908. Min Act: -0.1700

Data Index: 6897503 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.5150. Min Act: -0.1700

Data Index: 7536584 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.5024. Min Act: -0.1700

Data Index: 6263697 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.5025. Min Act: -0.1700

Data Index: 6354695 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4702. Min Act: -0.1700

Data Index: 1759349 (Open Web Text)

Max Activating Token Index: 240

Text #12

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4620. Min Act: -0.1700

Data Index: 445195 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4497. Min Act: -0.1700

Data Index: 2474752 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4476. Min Act: -0.1700

Data Index: 2766015 (Open Web Text)

Max Activating Token Index: 680

Text #15

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4415. Min Act: -0.1700

Data Index: 987531 (Open Web Text)

Max Activating Token Index: 475

Text #16

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4463. Min Act: -0.1700

Data Index: 7886677 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4029. Min Act: -0.1700

Data Index: 6241960 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4363. Min Act: -0.1700

Data Index: 1824270 (Open Web Text)

Max Activating Token Index: 749

Text #19

Max Range: 4.7421. Min Range: -4.7421

Max Act: 4.4267. Min Act: -0.1700

Data Index: 1748711 (Open Web Text)

Max Activating Token Index: 29