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

Dataset: Open Web Text

Neuron 759 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: 6.1699. Min Range: -6.1699

Max Act: 6.1699. Min Act: -0.1700

Data Index: 2747459 (Open Web Text)

Max Activating Token Index: 223

Text #1

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.7576. Min Act: -0.1700

Data Index: 578905 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.8288. Min Act: -0.1700

Data Index: 4171300 (Open Web Text)

Max Activating Token Index: 829

Text #3

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.7684. Min Act: -0.1700

Data Index: 1931893 (Open Web Text)

Max Activating Token Index: 625

Text #4

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.7510. Min Act: -0.1700

Data Index: 5557706 (Open Web Text)

Max Activating Token Index: 500

Text #5

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6824. Min Act: -0.1700

Data Index: 4936113 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6930. Min Act: -0.1700

Data Index: 3823453 (Open Web Text)

Max Activating Token Index: 966

Text #7

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6838. Min Act: -0.1700

Data Index: 824166 (Open Web Text)

Max Activating Token Index: 475

Text #8

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6698. Min Act: -0.1700

Data Index: 1606828 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6235. Min Act: -0.1700

Data Index: 3321362 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6248. Min Act: -0.1700

Data Index: 8588107 (Open Web Text)

Max Activating Token Index: 54

Text #11

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6311. Min Act: -0.1700

Data Index: 4775765 (Open Web Text)

Max Activating Token Index: 687

Text #12

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6145. Min Act: -0.1700

Data Index: 4683803 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6447. Min Act: -0.1700

Data Index: 735094 (Open Web Text)

Max Activating Token Index: 303

Text #14

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6116. Min Act: -0.1700

Data Index: 1638899 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6504. Min Act: -0.1700

Data Index: 6029726 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.5823. Min Act: -0.1700

Data Index: 2084218 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.6136. Min Act: -0.1700

Data Index: 7151318 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.5762. Min Act: -0.1700

Data Index: 617040 (Open Web Text)

Max Activating Token Index: 884

Text #19

Max Range: 6.1699. Min Range: -6.1699

Max Act: 5.5998. Min Act: -0.1700

Data Index: 1621952 (Open Web Text)

Max Activating Token Index: 182