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

Dataset: Open Web Text

Neuron 1606 in Layer 5

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: 3.9250. Min Range: -3.9250

Max Act: 3.9250. Min Act: -0.1700

Data Index: 3985734 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.8590. Min Act: -0.1700

Data Index: 2082653 (Open Web Text)

Max Activating Token Index: 758

Text #2

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.8328. Min Act: -0.1700

Data Index: 5857221 (Open Web Text)

Max Activating Token Index: 663

Text #3

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.8234. Min Act: -0.1700

Data Index: 4494805 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.8015. Min Act: -0.1700

Data Index: 5276161 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7831. Min Act: -0.1700

Data Index: 1851137 (Open Web Text)

Max Activating Token Index: 649

Text #6

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7698. Min Act: -0.1700

Data Index: 4397854 (Open Web Text)

Max Activating Token Index: 260

Text #7

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7604. Min Act: -0.1700

Data Index: 8481907 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7770. Min Act: -0.1700

Data Index: 3059000 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7034. Min Act: -0.1700

Data Index: 6002260 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7152. Min Act: -0.1700

Data Index: 1066518 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7133. Min Act: -0.1700

Data Index: 7718594 (Open Web Text)

Max Activating Token Index: 905

Text #12

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7341. Min Act: -0.1700

Data Index: 2555760 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7359. Min Act: -0.1700

Data Index: 977748 (Open Web Text)

Max Activating Token Index: 725

Text #14

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.6799. Min Act: -0.1700

Data Index: 7219327 (Open Web Text)

Max Activating Token Index: 921

Text #15

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7007. Min Act: -0.1700

Data Index: 235465 (Open Web Text)

Max Activating Token Index: 863

Text #16

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.6829. Min Act: -0.1700

Data Index: 474591 (Open Web Text)

Max Activating Token Index: 766

Text #17

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.7086. Min Act: -0.1700

Data Index: 3614948 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.6978. Min Act: -0.1700

Data Index: 4036321 (Open Web Text)

Max Activating Token Index: 678

Text #19

Max Range: 3.9250. Min Range: -3.9250

Max Act: 3.6892. Min Act: -0.1700

Data Index: 4137526 (Open Web Text)

Max Activating Token Index: 763