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

Dataset: Open Web Text

Neuron 1681 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: 3.0361. Min Range: -3.0361

Max Act: 3.0361. Min Act: -0.1700

Data Index: 8216180 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.0361. Min Range: -3.0361

Max Act: 3.0271. Min Act: -0.1700

Data Index: 1176357 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9941. Min Act: -0.1700

Data Index: 3892161 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9733. Min Act: -0.1700

Data Index: 7848950 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9588. Min Act: -0.1700

Data Index: 5395122 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9611. Min Act: -0.1700

Data Index: 1860546 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9633. Min Act: -0.1700

Data Index: 7671689 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9248. Min Act: -0.1700

Data Index: 2691482 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9226. Min Act: -0.1700

Data Index: 523914 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9066. Min Act: -0.1700

Data Index: 2167195 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9162. Min Act: -0.1700

Data Index: 4398232 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9146. Min Act: -0.1700

Data Index: 7468403 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9177. Min Act: -0.1700

Data Index: 6027628 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9146. Min Act: -0.1700

Data Index: 2735008 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9175. Min Act: -0.1700

Data Index: 1825169 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9101. Min Act: -0.1700

Data Index: 3625566 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9033. Min Act: -0.1700

Data Index: 2667787 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.9017. Min Act: -0.1700

Data Index: 5512162 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.8993. Min Act: -0.1700

Data Index: 6857469 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.0361. Min Range: -3.0361

Max Act: 2.8904. Min Act: -0.1700

Data Index: 7354751 (Open Web Text)

Max Activating Token Index: 3