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

Dataset: Open Web Text

Neuron 2571 in Layer 4

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: 3.8789. Min Range: -3.8789

Max Act: 3.8789. Min Act: -0.1700

Data Index: 4413234 (Open Web Text)

Max Activating Token Index: 326

Text #1

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7605. Min Act: -0.1700

Data Index: 8458037 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7774. Min Act: -0.1700

Data Index: 6873729 (Open Web Text)

Max Activating Token Index: 890

Text #3

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7330. Min Act: -0.1700

Data Index: 7174154 (Open Web Text)

Max Activating Token Index: 228

Text #4

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7649. Min Act: -0.1700

Data Index: 6025408 (Open Web Text)

Max Activating Token Index: 126

Text #5

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7014. Min Act: -0.1700

Data Index: 8405292 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.7863. Min Act: -0.1700

Data Index: 7087336 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6430. Min Act: -0.1700

Data Index: 8788087 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6888. Min Act: -0.1700

Data Index: 4278385 (Open Web Text)

Max Activating Token Index: 287

Text #9

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6387. Min Act: -0.1700

Data Index: 5491403 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6483. Min Act: -0.1700

Data Index: 1867661 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.5779. Min Act: -0.1700

Data Index: 7536028 (Open Web Text)

Max Activating Token Index: 157

Text #12

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6178. Min Act: -0.1700

Data Index: 8362919 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6335. Min Act: -0.1700

Data Index: 2701606 (Open Web Text)

Max Activating Token Index: 258

Text #14

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6203. Min Act: -0.1700

Data Index: 5811297 (Open Web Text)

Max Activating Token Index: 206

Text #15

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6627. Min Act: -0.1700

Data Index: 4272708 (Open Web Text)

Max Activating Token Index: 483

Text #16

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6521. Min Act: -0.1700

Data Index: 6900464 (Open Web Text)

Max Activating Token Index: 995

Text #17

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.6334. Min Act: -0.1700

Data Index: 7979612 (Open Web Text)

Max Activating Token Index: 960

Text #18

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.5803. Min Act: -0.1700

Data Index: 3373162 (Open Web Text)

Max Activating Token Index: 846

Text #19

Max Range: 3.8789. Min Range: -3.8789

Max Act: 3.5920. Min Act: -0.1700

Data Index: 2024327 (Open Web Text)

Max Activating Token Index: 693