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

Dataset: Open Web Text

Neuron 653 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: 4.1412. Min Range: -4.1412

Max Act: 4.1150. Min Act: -0.1700

Data Index: 4311897 (Open Web Text)

Max Activating Token Index: 633

Text #1

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.1412. Min Act: -0.1700

Data Index: 2341955 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0909. Min Act: -0.1700

Data Index: 7779843 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0954. Min Act: -0.1700

Data Index: 3932093 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0751. Min Act: -0.1700

Data Index: 7974732 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0696. Min Act: -0.1700

Data Index: 7192762 (Open Web Text)

Max Activating Token Index: 204

Text #6

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0862. Min Act: -0.1700

Data Index: 4002017 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0113. Min Act: -0.1700

Data Index: 925795 (Open Web Text)

Max Activating Token Index: 1016

Text #8

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0691. Min Act: -0.1700

Data Index: 8246040 (Open Web Text)

Max Activating Token Index: 824

Text #9

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0252. Min Act: -0.1700

Data Index: 3013539 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0312. Min Act: -0.1700

Data Index: 7353102 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0235. Min Act: -0.1700

Data Index: 3760584 (Open Web Text)

Max Activating Token Index: 86

Text #12

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0294. Min Act: -0.1700

Data Index: 601017 (Open Web Text)

Max Activating Token Index: 944

Text #13

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0276. Min Act: -0.1700

Data Index: 6471568 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 4.1412. Min Range: -4.1412

Max Act: 3.9728. Min Act: -0.1700

Data Index: 1500070 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 4.1412. Min Range: -4.1412

Max Act: 3.9656. Min Act: -0.1700

Data Index: 4828777 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 4.1412. Min Range: -4.1412

Max Act: 4.0085. Min Act: -0.1700

Data Index: 4881886 (Open Web Text)

Max Activating Token Index: 799

Text #17

Max Range: 4.1412. Min Range: -4.1412

Max Act: 3.9684. Min Act: -0.1700

Data Index: 1772197 (Open Web Text)

Max Activating Token Index: 55

Text #18

Max Range: 4.1412. Min Range: -4.1412

Max Act: 3.9855. Min Act: -0.1700

Data Index: 3052166 (Open Web Text)

Max Activating Token Index: 432

Text #19

Max Range: 4.1412. Min Range: -4.1412

Max Act: 3.9694. Min Act: -0.1700

Data Index: 6112607 (Open Web Text)

Max Activating Token Index: 100