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

Dataset: Open Web Text

Neuron 757 in Layer 1

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: 1.6901. Min Range: -1.6901

Max Act: 1.6882. Min Act: -0.1700

Data Index: 1288467 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6901. Min Act: -0.1700

Data Index: 2641867 (Open Web Text)

Max Activating Token Index: 888

Text #2

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6792. Min Act: -0.1700

Data Index: 5712394 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6717. Min Act: -0.1700

Data Index: 7726195 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6696. Min Act: -0.1700

Data Index: 2309929 (Open Web Text)

Max Activating Token Index: 659

Text #5

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6605. Min Act: -0.1700

Data Index: 1783081 (Open Web Text)

Max Activating Token Index: 73

Text #6

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6526. Min Act: -0.1700

Data Index: 1513287 (Open Web Text)

Max Activating Token Index: 286

Text #7

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6527. Min Act: -0.1700

Data Index: 6213522 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6511. Min Act: -0.1700

Data Index: 8437664 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6433. Min Act: -0.1700

Data Index: 6759374 (Open Web Text)

Max Activating Token Index: 267

Text #10

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6357. Min Act: -0.1700

Data Index: 3111691 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6269. Min Act: -0.1700

Data Index: 3084384 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6196. Min Act: -0.1700

Data Index: 8385966 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6197. Min Act: -0.1700

Data Index: 1643581 (Open Web Text)

Max Activating Token Index: 365

Text #14

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6304. Min Act: -0.1700

Data Index: 3845927 (Open Web Text)

Max Activating Token Index: 792

Text #15

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6221. Min Act: -0.1700

Data Index: 6530041 (Open Web Text)

Max Activating Token Index: 244

Text #16

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6173. Min Act: -0.1700

Data Index: 3742377 (Open Web Text)

Max Activating Token Index: 869

Text #17

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6113. Min Act: -0.1700

Data Index: 5431812 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6157. Min Act: -0.1700

Data Index: 1437336 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 1.6901. Min Range: -1.6901

Max Act: 1.6123. Min Act: -0.1700

Data Index: 2448775 (Open Web Text)

Max Activating Token Index: 700