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

Dataset: Open Web Text

Neuron 62 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: 4.8932. Min Range: -4.8932

Max Act: 4.8932. Min Act: -0.1700

Data Index: 5585846 (Open Web Text)

Max Activating Token Index: 278

Text #1

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.8660. Min Act: -0.1700

Data Index: 7634812 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.8615. Min Act: -0.1700

Data Index: 5494064 (Open Web Text)

Max Activating Token Index: 303

Text #3

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.8481. Min Act: -0.1700

Data Index: 7436714 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.8422. Min Act: -0.1700

Data Index: 6511904 (Open Web Text)

Max Activating Token Index: 592

Text #5

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.8189. Min Act: -0.1700

Data Index: 1600926 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7875. Min Act: -0.1700

Data Index: 3154957 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.8295. Min Act: -0.1700

Data Index: 6677465 (Open Web Text)

Max Activating Token Index: 971

Text #8

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7654. Min Act: -0.1700

Data Index: 2350838 (Open Web Text)

Max Activating Token Index: 952

Text #9

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7313. Min Act: -0.1700

Data Index: 773301 (Open Web Text)

Max Activating Token Index: 872

Text #10

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7702. Min Act: -0.1700

Data Index: 4516089 (Open Web Text)

Max Activating Token Index: 116

Text #11

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7516. Min Act: -0.1700

Data Index: 8164580 (Open Web Text)

Max Activating Token Index: 106

Text #12

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7576. Min Act: -0.1700

Data Index: 6455672 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7284. Min Act: -0.1700

Data Index: 5407551 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.6452. Min Act: -0.1700

Data Index: 7692612 (Open Web Text)

Max Activating Token Index: 889

Text #15

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7371. Min Act: -0.1700

Data Index: 2322243 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7184. Min Act: -0.1700

Data Index: 1404745 (Open Web Text)

Max Activating Token Index: 525

Text #17

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7031. Min Act: -0.1700

Data Index: 3354053 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.7222. Min Act: -0.1700

Data Index: 5567889 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 4.8932. Min Range: -4.8932

Max Act: 4.6912. Min Act: -0.1700

Data Index: 5567891 (Open Web Text)

Max Activating Token Index: 5