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

Dataset: Open Web Text

Neuron 601 in Layer 1

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: 1.4720. Min Range: -1.4720

Max Act: 1.4720. Min Act: -0.1700

Data Index: 6670337 (Open Web Text)

Max Activating Token Index: 598

Text #1

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4500. Min Act: -0.1699

Data Index: 6810003 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4394. Min Act: -0.1700

Data Index: 147228 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4192. Min Act: -0.1700

Data Index: 5417818 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4222. Min Act: -0.1700

Data Index: 3895304 (Open Web Text)

Max Activating Token Index: 437

Text #5

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4164. Min Act: -0.1700

Data Index: 4658310 (Open Web Text)

Max Activating Token Index: 912

Text #6

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4253. Min Act: -0.1700

Data Index: 4653795 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4149. Min Act: -0.1700

Data Index: 8574459 (Open Web Text)

Max Activating Token Index: 197

Text #8

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4137. Min Act: -0.1700

Data Index: 8550507 (Open Web Text)

Max Activating Token Index: 158

Text #9

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4103. Min Act: -0.1700

Data Index: 4412179 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4132. Min Act: -0.1700

Data Index: 5380010 (Open Web Text)

Max Activating Token Index: 325

Text #11

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4001. Min Act: -0.1700

Data Index: 8777922 (Open Web Text)

Max Activating Token Index: 709

Text #12

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.3980. Min Act: -0.1700

Data Index: 5140542 (Open Web Text)

Max Activating Token Index: 221

Text #13

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4066. Min Act: -0.1700

Data Index: 1263471 (Open Web Text)

Max Activating Token Index: 282

Text #14

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.3935. Min Act: -0.1700

Data Index: 3635851 (Open Web Text)

Max Activating Token Index: 311

Text #15

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4041. Min Act: -0.1697

Data Index: 4275722 (Open Web Text)

Max Activating Token Index: 481

Text #16

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4008. Min Act: -0.1700

Data Index: 7276626 (Open Web Text)

Max Activating Token Index: 632

Text #17

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.3907. Min Act: -0.1700

Data Index: 5757449 (Open Web Text)

Max Activating Token Index: 302

Text #18

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.4015. Min Act: -0.1700

Data Index: 5635941 (Open Web Text)

Max Activating Token Index: 911

Text #19

Max Range: 1.4720. Min Range: -1.4720

Max Act: 1.3927. Min Act: -0.1699

Data Index: 6997158 (Open Web Text)

Max Activating Token Index: 704