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

Dataset: Open Web Text

Neuron 1947 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: 4.5088. Min Range: -4.5088

Max Act: 4.4311. Min Act: -0.1700

Data Index: 6953680 (Open Web Text)

Max Activating Token Index: 350

Text #1

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.5088. Min Act: -0.1700

Data Index: 1373271 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.3623. Min Act: -0.1700

Data Index: 4459815 (Open Web Text)

Max Activating Token Index: 740

Text #3

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.3158. Min Act: -0.1700

Data Index: 2996856 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.3270. Min Act: -0.1700

Data Index: 4049108 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.3265. Min Act: -0.1700

Data Index: 898078 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.2754. Min Act: -0.1700

Data Index: 4459814 (Open Web Text)

Max Activating Token Index: 894

Text #7

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.3045. Min Act: -0.1700

Data Index: 4548696 (Open Web Text)

Max Activating Token Index: 397

Text #8

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.3227. Min Act: -0.1700

Data Index: 6619466 (Open Web Text)

Max Activating Token Index: 401

Text #9

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.2580. Min Act: -0.1700

Data Index: 8392235 (Open Web Text)

Max Activating Token Index: 277

Text #10

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.2766. Min Act: -0.1700

Data Index: 885971 (Open Web Text)

Max Activating Token Index: 709

Text #11

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.2211. Min Act: -0.1700

Data Index: 7442608 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.2448. Min Act: -0.1700

Data Index: 3802130 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.1892. Min Act: -0.1700

Data Index: 5196515 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.2236. Min Act: -0.1700

Data Index: 4997108 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.2038. Min Act: -0.1700

Data Index: 4825509 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.2247. Min Act: -0.1700

Data Index: 2224535 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.1670. Min Act: -0.1700

Data Index: 1533554 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.1814. Min Act: -0.1700

Data Index: 1434757 (Open Web Text)

Max Activating Token Index: 758

Text #19

Max Range: 4.5088. Min Range: -4.5088

Max Act: 4.1480. Min Act: -0.1700

Data Index: 1989024 (Open Web Text)

Max Activating Token Index: 2