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

Dataset: Open Web Text

Neuron 2644 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: 7.4180. Min Range: -7.4180

Max Act: 7.4180. Min Act: -0.1700

Data Index: 6001734 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 7.4180. Min Range: -7.4180

Max Act: 7.3390. Min Act: -0.1700

Data Index: 4579402 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 7.4180. Min Range: -7.4180

Max Act: 7.2010. Min Act: -0.1700

Data Index: 6401412 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 7.4180. Min Range: -7.4180

Max Act: 7.1464. Min Act: -0.1700

Data Index: 6124941 (Open Web Text)

Max Activating Token Index: 996

Text #4

Max Range: 7.4180. Min Range: -7.4180

Max Act: 7.1507. Min Act: -0.1700

Data Index: 5231140 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 7.4180. Min Range: -7.4180

Max Act: 7.1461. Min Act: -0.1700

Data Index: 3970892 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 7.4180. Min Range: -7.4180

Max Act: 7.1180. Min Act: -0.1700

Data Index: 5118118 (Open Web Text)

Max Activating Token Index: 1006

Text #7

Max Range: 7.4180. Min Range: -7.4180

Max Act: 7.1077. Min Act: -0.1700

Data Index: 5216595 (Open Web Text)

Max Activating Token Index: 936

Text #8

Max Range: 7.4180. Min Range: -7.4180

Max Act: 7.0625. Min Act: -0.1700

Data Index: 5609457 (Open Web Text)

Max Activating Token Index: 1009

Text #9

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.9650. Min Act: -0.1700

Data Index: 7123445 (Open Web Text)

Max Activating Token Index: 939

Text #10

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.9413. Min Act: -0.1700

Data Index: 6217247 (Open Web Text)

Max Activating Token Index: 997

Text #11

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.9306. Min Act: -0.1700

Data Index: 2904430 (Open Web Text)

Max Activating Token Index: 1006

Text #12

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.9501. Min Act: -0.1700

Data Index: 3394727 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.8436. Min Act: -0.1700

Data Index: 3394623 (Open Web Text)

Max Activating Token Index: 874

Text #14

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.8653. Min Act: -0.1700

Data Index: 3941308 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.8572. Min Act: -0.1700

Data Index: 562692 (Open Web Text)

Max Activating Token Index: 963

Text #16

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.8728. Min Act: -0.1700

Data Index: 3661065 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.8184. Min Act: -0.1700

Data Index: 5188431 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.8517. Min Act: -0.1700

Data Index: 3297703 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 7.4180. Min Range: -7.4180

Max Act: 6.8408. Min Act: -0.1700

Data Index: 4718807 (Open Web Text)

Max Activating Token Index: 994