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

Dataset: Open Web Text

Neuron 2879 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: 3.7446. Min Range: -3.7446

Max Act: 3.7446. Min Act: -0.1700

Data Index: 8140390 (Open Web Text)

Max Activating Token Index: 545

Text #1

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.5055. Min Act: -0.1700

Data Index: 2162574 (Open Web Text)

Max Activating Token Index: 334

Text #2

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4322. Min Act: -0.1700

Data Index: 1857656 (Open Web Text)

Max Activating Token Index: 177

Text #3

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4126. Min Act: -0.1700

Data Index: 7728477 (Open Web Text)

Max Activating Token Index: 568

Text #4

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4492. Min Act: -0.1700

Data Index: 650292 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4105. Min Act: -0.1700

Data Index: 3945322 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4225. Min Act: -0.1700

Data Index: 5597137 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4151. Min Act: -0.1700

Data Index: 6194257 (Open Web Text)

Max Activating Token Index: 170

Text #8

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4000. Min Act: -0.1700

Data Index: 5467778 (Open Web Text)

Max Activating Token Index: 756

Text #9

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4006. Min Act: -0.1700

Data Index: 918777 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4470. Min Act: -0.1700

Data Index: 8259047 (Open Web Text)

Max Activating Token Index: 326

Text #11

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.3745. Min Act: -0.1700

Data Index: 4470881 (Open Web Text)

Max Activating Token Index: 506

Text #12

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.3869. Min Act: -0.1700

Data Index: 320441 (Open Web Text)

Max Activating Token Index: 44

Text #13

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4119. Min Act: -0.1700

Data Index: 2643872 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.4013. Min Act: -0.1700

Data Index: 8252034 (Open Web Text)

Max Activating Token Index: 379

Text #15

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.3701. Min Act: -0.1700

Data Index: 195141 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.3708. Min Act: -0.1700

Data Index: 4242274 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.3310. Min Act: -0.1700

Data Index: 7818607 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.3342. Min Act: -0.1700

Data Index: 8196330 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 3.7446. Min Range: -3.7446

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1360362 (Open Web Text)

Max Activating Token Index: 448