Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 2509 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.9064. Min Act: -0.1700

Data Index: 2823808 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.8751. Min Act: -0.1700

Data Index: 3971654 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.8439. Min Act: -0.1696

Data Index: 504303 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.7501. Min Act: -0.1699

Data Index: 334085 (Open Web Text)

Max Activating Token Index: 23

Text #4

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.6876. Min Act: -0.1699

Data Index: 415444 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.6876. Min Act: -0.1700

Data Index: 6163750 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.6564. Min Act: -0.1700

Data Index: 726223 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.6251. Min Act: -0.1653

Data Index: 3866663 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.5939. Min Act: -0.1688

Data Index: 5298340 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.5939. Min Act: -0.1700

Data Index: 1728803 (Open Web Text)

Max Activating Token Index: 149

Text #10

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.5626. Min Act: -0.1700

Data Index: 3420383 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.5626. Min Act: -0.1700

Data Index: 5478460 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.5626. Min Act: -0.1700

Data Index: 4012226 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.5626. Min Act: -0.1700

Data Index: 4996911 (Open Web Text)

Max Activating Token Index: 30

Text #14

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.5001. Min Act: -0.1630

Data Index: 5276742 (Open Web Text)

Max Activating Token Index: 501

Text #15

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.5001. Min Act: -0.1700

Data Index: 5298341 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.4376. Min Act: -0.1700

Data Index: 4816724 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.4376. Min Act: -0.1700

Data Index: 7870984 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.4376. Min Act: -0.1699

Data Index: 7019862 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 5.9064. Min Range: -5.9064

Max Act: 5.4064. Min Act: -0.1700

Data Index: 5392292 (Open Web Text)

Max Activating Token Index: 476