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

Dataset: Open Web Text

Neuron 1692 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: 2.4917. Min Range: -2.4917

Max Act: 2.4917. Min Act: -0.1700

Data Index: 8634749 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4862. Min Act: -0.1700

Data Index: 6622175 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4729. Min Act: -0.1700

Data Index: 6159739 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4308. Min Act: -0.1700

Data Index: 5424852 (Open Web Text)

Max Activating Token Index: 371

Text #4

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4353. Min Act: -0.1700

Data Index: 6531459 (Open Web Text)

Max Activating Token Index: 493

Text #5

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4226. Min Act: -0.1700

Data Index: 8426803 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3856. Min Act: -0.1700

Data Index: 6253894 (Open Web Text)

Max Activating Token Index: 899

Text #7

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4095. Min Act: -0.1700

Data Index: 2390654 (Open Web Text)

Max Activating Token Index: 800

Text #8

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4123. Min Act: -0.1700

Data Index: 7367965 (Open Web Text)

Max Activating Token Index: 92

Text #9

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4044. Min Act: -0.1700

Data Index: 936034 (Open Web Text)

Max Activating Token Index: 43

Text #10

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3873. Min Act: -0.1700

Data Index: 3025103 (Open Web Text)

Max Activating Token Index: 834

Text #11

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3573. Min Act: -0.1700

Data Index: 1845840 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3768. Min Act: -0.1700

Data Index: 7564480 (Open Web Text)

Max Activating Token Index: 671

Text #13

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3916. Min Act: -0.1700

Data Index: 5581244 (Open Web Text)

Max Activating Token Index: 472

Text #14

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.4046. Min Act: -0.1700

Data Index: 5061975 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3562. Min Act: -0.1700

Data Index: 913180 (Open Web Text)

Max Activating Token Index: 905

Text #16

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3376. Min Act: -0.1700

Data Index: 5447145 (Open Web Text)

Max Activating Token Index: 560

Text #17

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3512. Min Act: -0.1700

Data Index: 7451010 (Open Web Text)

Max Activating Token Index: 700

Text #18

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3637. Min Act: -0.1700

Data Index: 3676965 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 2.4917. Min Range: -2.4917

Max Act: 2.3517. Min Act: -0.1700

Data Index: 5396152 (Open Web Text)

Max Activating Token Index: 493