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

Dataset: Open Web Text

Neuron 821 in Layer 0

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: 6.0089. Min Range: -6.0089

Max Act: 6.0089. Min Act: -0.1700

Data Index: 754056 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.9475. Min Act: -0.1700

Data Index: 2137312 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.8859. Min Act: -0.1700

Data Index: 6432987 (Open Web Text)

Max Activating Token Index: 164

Text #3

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.8759. Min Act: -0.1700

Data Index: 5876184 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.8823. Min Act: -0.1700

Data Index: 1127082 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.8420. Min Act: -0.1700

Data Index: 6063137 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.8011. Min Act: -0.1700

Data Index: 1599243 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.7768. Min Act: -0.1700

Data Index: 4985791 (Open Web Text)

Max Activating Token Index: 492

Text #8

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.8089. Min Act: -0.1700

Data Index: 2674597 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.7723. Min Act: -0.1700

Data Index: 2600376 (Open Web Text)

Max Activating Token Index: 693

Text #10

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.7701. Min Act: -0.1700

Data Index: 1846953 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.7701. Min Act: -0.1700

Data Index: 2225800 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.7565. Min Act: -0.1700

Data Index: 2835109 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.7374. Min Act: -0.1700

Data Index: 5553147 (Open Web Text)

Max Activating Token Index: 163

Text #14

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.7037. Min Act: -0.1700

Data Index: 3328607 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.6931. Min Act: -0.1700

Data Index: 6196027 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.6927. Min Act: -0.1700

Data Index: 6771150 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.6992. Min Act: -0.1700

Data Index: 729857 (Open Web Text)

Max Activating Token Index: 180

Text #18

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.6778. Min Act: -0.1700

Data Index: 4497053 (Open Web Text)

Max Activating Token Index: 709

Text #19

Max Range: 6.0089. Min Range: -6.0089

Max Act: 5.6709. Min Act: -0.1700

Data Index: 5204208 (Open Web Text)

Max Activating Token Index: 11