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

Dataset: Open Web Text

Neuron 2682 in Layer 2

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: 1.7857. Min Range: -1.7857

Max Act: 1.7835. Min Act: -0.1700

Data Index: 2361407 (Open Web Text)

Max Activating Token Index: 700

Text #1

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7749. Min Act: -0.1698

Data Index: 1581917 (Open Web Text)

Max Activating Token Index: 295

Text #2

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7857. Min Act: -0.1700

Data Index: 256870 (Open Web Text)

Max Activating Token Index: 743

Text #3

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7514. Min Act: -0.1700

Data Index: 5373320 (Open Web Text)

Max Activating Token Index: 693

Text #4

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7212. Min Act: -0.1700

Data Index: 2361408 (Open Web Text)

Max Activating Token Index: 196

Text #5

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7409. Min Act: -0.1700

Data Index: 1355930 (Open Web Text)

Max Activating Token Index: 710

Text #6

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6833. Min Act: -0.1700

Data Index: 1529751 (Open Web Text)

Max Activating Token Index: 682

Text #7

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6905. Min Act: -0.1700

Data Index: 8736497 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7068. Min Act: -0.1700

Data Index: 3195163 (Open Web Text)

Max Activating Token Index: 195

Text #9

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6961. Min Act: -0.1699

Data Index: 563178 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7153. Min Act: -0.1700

Data Index: 1883683 (Open Web Text)

Max Activating Token Index: 723

Text #11

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7110. Min Act: -0.1697

Data Index: 1068089 (Open Web Text)

Max Activating Token Index: 583

Text #12

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7162. Min Act: -0.1700

Data Index: 5285813 (Open Web Text)

Max Activating Token Index: 678

Text #13

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7189. Min Act: -0.1700

Data Index: 465031 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7107. Min Act: -0.1699

Data Index: 2835754 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.7032. Min Act: -0.1700

Data Index: 3971175 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6917. Min Act: -0.1698

Data Index: 740099 (Open Web Text)

Max Activating Token Index: 556

Text #17

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6791. Min Act: -0.1700

Data Index: 6725888 (Open Web Text)

Max Activating Token Index: 89

Text #18

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6812. Min Act: -0.1700

Data Index: 6220734 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 1.7857. Min Range: -1.7857

Max Act: 1.6740. Min Act: -0.1700

Data Index: 5671814 (Open Web Text)

Max Activating Token Index: 152