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

Dataset: Open Web Text

Neuron 223 in Layer 3

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: 3.8013. Min Range: -3.8013

Max Act: 3.8013. Min Act: -0.1700

Data Index: 8627506 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7549. Min Act: -0.1700

Data Index: 7452060 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.7508. Min Act: -0.1700

Data Index: 3686475 (Open Web Text)

Max Activating Token Index: 834

Text #3

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6653. Min Act: -0.1700

Data Index: 6328486 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6765. Min Act: -0.1700

Data Index: 509051 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6821. Min Act: -0.1700

Data Index: 6187085 (Open Web Text)

Max Activating Token Index: 272

Text #6

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6695. Min Act: -0.1700

Data Index: 4824231 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6739. Min Act: -0.1700

Data Index: 4263596 (Open Web Text)

Max Activating Token Index: 895

Text #8

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6507. Min Act: -0.1700

Data Index: 2755931 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6602. Min Act: -0.1700

Data Index: 8017435 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6878. Min Act: -0.1700

Data Index: 684837 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6564. Min Act: -0.1700

Data Index: 6918950 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6522. Min Act: -0.1700

Data Index: 6750929 (Open Web Text)

Max Activating Token Index: 44

Text #13

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6696. Min Act: -0.1700

Data Index: 8084676 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6266. Min Act: -0.1700

Data Index: 928629 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6129. Min Act: -0.1700

Data Index: 3632651 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.5897. Min Act: -0.1700

Data Index: 2678526 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6118. Min Act: -0.1700

Data Index: 6990341 (Open Web Text)

Max Activating Token Index: 848

Text #18

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.6180. Min Act: -0.1700

Data Index: 4483703 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 3.8013. Min Range: -3.8013

Max Act: 3.5982. Min Act: -0.1700

Data Index: 4771198 (Open Web Text)

Max Activating Token Index: 153