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

Dataset: Open Web Text

Neuron 658 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: 4.0006. Min Range: -4.0006

Max Act: 4.0006. Min Act: -0.1700

Data Index: 875467 (Open Web Text)

Max Activating Token Index: 721

Text #1

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8959. Min Act: -0.1700

Data Index: 6847493 (Open Web Text)

Max Activating Token Index: 275

Text #2

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.9047. Min Act: -0.1700

Data Index: 8061388 (Open Web Text)

Max Activating Token Index: 634

Text #3

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8883. Min Act: -0.1700

Data Index: 5278519 (Open Web Text)

Max Activating Token Index: 305

Text #4

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8690. Min Act: -0.1700

Data Index: 6508704 (Open Web Text)

Max Activating Token Index: 244

Text #5

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8371. Min Act: -0.1700

Data Index: 4008109 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8284. Min Act: -0.1700

Data Index: 8229889 (Open Web Text)

Max Activating Token Index: 788

Text #7

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8476. Min Act: -0.1700

Data Index: 5912018 (Open Web Text)

Max Activating Token Index: 796

Text #8

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8360. Min Act: -0.1700

Data Index: 5991965 (Open Web Text)

Max Activating Token Index: 375

Text #9

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8371. Min Act: -0.1700

Data Index: 8381712 (Open Web Text)

Max Activating Token Index: 236

Text #10

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8279. Min Act: -0.1700

Data Index: 8396049 (Open Web Text)

Max Activating Token Index: 435

Text #11

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8059. Min Act: -0.1700

Data Index: 4660677 (Open Web Text)

Max Activating Token Index: 260

Text #12

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8045. Min Act: -0.1700

Data Index: 5525790 (Open Web Text)

Max Activating Token Index: 667

Text #13

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8275. Min Act: -0.1700

Data Index: 1262768 (Open Web Text)

Max Activating Token Index: 878

Text #14

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.8177. Min Act: -0.1700

Data Index: 3490018 (Open Web Text)

Max Activating Token Index: 910

Text #15

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.7944. Min Act: -0.1700

Data Index: 340008 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.7918. Min Act: -0.1700

Data Index: 2913549 (Open Web Text)

Max Activating Token Index: 285

Text #17

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.7758. Min Act: -0.1700

Data Index: 6129338 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.7828. Min Act: -0.1700

Data Index: 5127735 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 4.0006. Min Range: -4.0006

Max Act: 3.7838. Min Act: -0.1700

Data Index: 5033298 (Open Web Text)

Max Activating Token Index: 85