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

Dataset: Open Web Text

Neuron 2904 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: 4.6846. Min Range: -4.6846

Max Act: 4.6846. Min Act: -0.1700

Data Index: 408247 (Open Web Text)

Max Activating Token Index: 408

Text #1

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6506. Min Act: -0.1700

Data Index: 7720080 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6342. Min Act: -0.1700

Data Index: 7626519 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6593. Min Act: -0.1700

Data Index: 5924754 (Open Web Text)

Max Activating Token Index: 410

Text #4

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6353. Min Act: -0.1700

Data Index: 3598736 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6114. Min Act: -0.1700

Data Index: 344791 (Open Web Text)

Max Activating Token Index: 594

Text #6

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6080. Min Act: -0.1700

Data Index: 2671329 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6029. Min Act: -0.1700

Data Index: 6321267 (Open Web Text)

Max Activating Token Index: 335

Text #8

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6185. Min Act: -0.1700

Data Index: 6311855 (Open Web Text)

Max Activating Token Index: 373

Text #9

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6007. Min Act: -0.1700

Data Index: 6214771 (Open Web Text)

Max Activating Token Index: 343

Text #10

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6110. Min Act: -0.1700

Data Index: 5732934 (Open Web Text)

Max Activating Token Index: 320

Text #11

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6053. Min Act: -0.1700

Data Index: 1636935 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6136. Min Act: -0.1700

Data Index: 5576647 (Open Web Text)

Max Activating Token Index: 343

Text #13

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6125. Min Act: -0.1700

Data Index: 5174226 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6022. Min Act: -0.1700

Data Index: 1344647 (Open Web Text)

Max Activating Token Index: 362

Text #15

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6056. Min Act: -0.1700

Data Index: 1276324 (Open Web Text)

Max Activating Token Index: 551

Text #16

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6176. Min Act: -0.1700

Data Index: 1267614 (Open Web Text)

Max Activating Token Index: 207

Text #17

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6086. Min Act: -0.1700

Data Index: 26691 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6001. Min Act: -0.1700

Data Index: 1254800 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 4.6846. Min Range: -4.6846

Max Act: 4.6181. Min Act: -0.1700

Data Index: 4152825 (Open Web Text)

Max Activating Token Index: 440