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

Dataset: Open Web Text

Neuron 2940 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: 1.9116. Min Range: -1.9116

Max Act: 1.9116. Min Act: -0.1700

Data Index: 1601286 (Open Web Text)

Max Activating Token Index: 360

Text #1

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7950. Min Act: -0.1700

Data Index: 3441567 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.8152. Min Act: -0.1700

Data Index: 368074 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.8083. Min Act: -0.1700

Data Index: 1035505 (Open Web Text)

Max Activating Token Index: 162

Text #4

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.8070. Min Act: -0.1700

Data Index: 8433718 (Open Web Text)

Max Activating Token Index: 554

Text #5

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.8175. Min Act: -0.1699

Data Index: 4225815 (Open Web Text)

Max Activating Token Index: 728

Text #6

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.8048. Min Act: -0.1700

Data Index: 3585301 (Open Web Text)

Max Activating Token Index: 406

Text #7

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.8075. Min Act: -0.1700

Data Index: 8077439 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.8099. Min Act: -0.1700

Data Index: 1019653 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.8125. Min Act: -0.1700

Data Index: 3495415 (Open Web Text)

Max Activating Token Index: 703

Text #10

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7974. Min Act: -0.1700

Data Index: 377689 (Open Web Text)

Max Activating Token Index: 675

Text #11

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7921. Min Act: -0.1700

Data Index: 6310529 (Open Web Text)

Max Activating Token Index: 522

Text #12

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7835. Min Act: -0.1700

Data Index: 5917782 (Open Web Text)

Max Activating Token Index: 490

Text #13

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7965. Min Act: -0.1700

Data Index: 2131125 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7981. Min Act: -0.1700

Data Index: 3824175 (Open Web Text)

Max Activating Token Index: 482

Text #15

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7910. Min Act: -0.1699

Data Index: 4495533 (Open Web Text)

Max Activating Token Index: 443

Text #16

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7828. Min Act: -0.1700

Data Index: 3438569 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7797. Min Act: -0.1700

Data Index: 6060396 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7725. Min Act: -0.1700

Data Index: 8620633 (Open Web Text)

Max Activating Token Index: 776

Text #19

Max Range: 1.9116. Min Range: -1.9116

Max Act: 1.7699. Min Act: -0.1700

Data Index: 2519055 (Open Web Text)

Max Activating Token Index: 514