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

Dataset: Open Web Text

Neuron 2664 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: 3.2642. Min Range: -3.2642

Max Act: 3.2642. Min Act: -0.1700

Data Index: 3964240 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1786. Min Act: -0.1700

Data Index: 711101 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1614. Min Act: -0.1700

Data Index: 8149338 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1421. Min Act: -0.1700

Data Index: 8781697 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1292. Min Act: -0.1700

Data Index: 2917590 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1304. Min Act: -0.1700

Data Index: 6800341 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1021. Min Act: -0.1700

Data Index: 115298 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.1066. Min Act: -0.1700

Data Index: 3667771 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0863. Min Act: -0.1700

Data Index: 5204507 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0816. Min Act: -0.1700

Data Index: 2928532 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0856. Min Act: -0.1700

Data Index: 6961196 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0856. Min Act: -0.1700

Data Index: 3120134 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0686. Min Act: -0.1700

Data Index: 8655807 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0801. Min Act: -0.1700

Data Index: 6881856 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0692. Min Act: -0.1700

Data Index: 2409000 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0669. Min Act: -0.1700

Data Index: 7103839 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0687. Min Act: -0.1700

Data Index: 7143641 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0298. Min Act: -0.1700

Data Index: 4177352 (Open Web Text)

Max Activating Token Index: 62

Text #18

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0461. Min Act: -0.1700

Data Index: 5332911 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.2642. Min Range: -3.2642

Max Act: 3.0434. Min Act: -0.1700

Data Index: 4438609 (Open Web Text)

Max Activating Token Index: 2