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

Dataset: Open Web Text

Neuron 2504 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: 4.2265. Min Range: -4.2265

Max Act: 4.2243. Min Act: -0.1700

Data Index: 2591525 (Open Web Text)

Max Activating Token Index: 621

Text #1

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.2265. Min Act: -0.1700

Data Index: 4607028 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.1711. Min Act: -0.1700

Data Index: 4078655 (Open Web Text)

Max Activating Token Index: 43

Text #3

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.1279. Min Act: -0.1700

Data Index: 5825113 (Open Web Text)

Max Activating Token Index: 238

Text #4

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.1203. Min Act: -0.1700

Data Index: 4554462 (Open Web Text)

Max Activating Token Index: 316

Text #5

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.1175. Min Act: -0.1700

Data Index: 4412620 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.1047. Min Act: -0.1700

Data Index: 7858081 (Open Web Text)

Max Activating Token Index: 480

Text #7

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.1025. Min Act: -0.1700

Data Index: 2790947 (Open Web Text)

Max Activating Token Index: 437

Text #8

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0935. Min Act: -0.1700

Data Index: 641877 (Open Web Text)

Max Activating Token Index: 731

Text #9

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.1040. Min Act: -0.1700

Data Index: 4118574 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0944. Min Act: -0.1700

Data Index: 2462017 (Open Web Text)

Max Activating Token Index: 320

Text #11

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0997. Min Act: -0.1700

Data Index: 5914639 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0478. Min Act: -0.1700

Data Index: 1335059 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0689. Min Act: -0.1700

Data Index: 782250 (Open Web Text)

Max Activating Token Index: 685

Text #14

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0774. Min Act: -0.1700

Data Index: 4463931 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0736. Min Act: -0.1700

Data Index: 2522203 (Open Web Text)

Max Activating Token Index: 38

Text #16

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0733. Min Act: -0.1700

Data Index: 3299442 (Open Web Text)

Max Activating Token Index: 958

Text #17

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0518. Min Act: -0.1700

Data Index: 1756910 (Open Web Text)

Max Activating Token Index: 653

Text #18

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0613. Min Act: -0.1700

Data Index: 2054851 (Open Web Text)

Max Activating Token Index: 461

Text #19

Max Range: 4.2265. Min Range: -4.2265

Max Act: 4.0429. Min Act: -0.1700

Data Index: 1959918 (Open Web Text)

Max Activating Token Index: 520