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

Dataset: Open Web Text

Neuron 729 in Layer 3

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: 3.3758. Min Range: -3.3758

Max Act: 3.3758. Min Act: -0.1700

Data Index: 7335454 (Open Web Text)

Max Activating Token Index: 350

Text #1

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2098. Min Act: -0.1700

Data Index: 1904554 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1750. Min Act: -0.1700

Data Index: 3038997 (Open Web Text)

Max Activating Token Index: 379

Text #3

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1935. Min Act: -0.1700

Data Index: 679008 (Open Web Text)

Max Activating Token Index: 490

Text #4

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1604. Min Act: -0.1700

Data Index: 679009 (Open Web Text)

Max Activating Token Index: 187

Text #5

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1478. Min Act: -0.1700

Data Index: 6129177 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1129. Min Act: -0.1700

Data Index: 6741533 (Open Web Text)

Max Activating Token Index: 139

Text #7

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1206. Min Act: -0.1700

Data Index: 8206451 (Open Web Text)

Max Activating Token Index: 285

Text #8

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1249. Min Act: -0.1700

Data Index: 6303296 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1058. Min Act: -0.1700

Data Index: 4440193 (Open Web Text)

Max Activating Token Index: 130

Text #10

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0777. Min Act: -0.1700

Data Index: 4016948 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0839. Min Act: -0.1700

Data Index: 5745049 (Open Web Text)

Max Activating Token Index: 778

Text #12

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0795. Min Act: -0.1700

Data Index: 8732230 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0881. Min Act: -0.1700

Data Index: 6516696 (Open Web Text)

Max Activating Token Index: 407

Text #14

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0737. Min Act: -0.1700

Data Index: 2029401 (Open Web Text)

Max Activating Token Index: 719

Text #15

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0619. Min Act: -0.1700

Data Index: 2504154 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0873. Min Act: -0.1700

Data Index: 2004167 (Open Web Text)

Max Activating Token Index: 906

Text #17

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0175. Min Act: -0.1700

Data Index: 6591603 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0426. Min Act: -0.1700

Data Index: 2556506 (Open Web Text)

Max Activating Token Index: 353

Text #19

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.0505. Min Act: -0.1700

Data Index: 596576 (Open Web Text)

Max Activating Token Index: 399