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

Dataset: Open Web Text

Neuron 1629 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: 4.3381. Min Range: -4.3381

Max Act: 4.3381. Min Act: -0.1700

Data Index: 1875136 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 4.3381. Min Range: -4.3381

Max Act: 4.1092. Min Act: -0.1700

Data Index: 8058240 (Open Web Text)

Max Activating Token Index: 586

Text #2

Max Range: 4.3381. Min Range: -4.3381

Max Act: 4.0473. Min Act: -0.1700

Data Index: 3343320 (Open Web Text)

Max Activating Token Index: 811

Text #3

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.9830. Min Act: -0.1700

Data Index: 904268 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.9213. Min Act: -0.1700

Data Index: 3524663 (Open Web Text)

Max Activating Token Index: 961

Text #5

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.8487. Min Act: -0.1700

Data Index: 2790975 (Open Web Text)

Max Activating Token Index: 609

Text #6

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.8837. Min Act: -0.1700

Data Index: 7343476 (Open Web Text)

Max Activating Token Index: 298

Text #7

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.8594. Min Act: -0.1700

Data Index: 6708960 (Open Web Text)

Max Activating Token Index: 231

Text #8

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.8814. Min Act: -0.1700

Data Index: 4104156 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.8527. Min Act: -0.1700

Data Index: 6044382 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.7617. Min Act: -0.1700

Data Index: 8245575 (Open Web Text)

Max Activating Token Index: 92

Text #11

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.7990. Min Act: -0.1700

Data Index: 7193525 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.7729. Min Act: -0.1700

Data Index: 7023937 (Open Web Text)

Max Activating Token Index: 696

Text #13

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.8012. Min Act: -0.1700

Data Index: 6048714 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.8052. Min Act: -0.1700

Data Index: 8193050 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.7829. Min Act: -0.1700

Data Index: 8450617 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.7990. Min Act: -0.1700

Data Index: 2896085 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.7765. Min Act: -0.1700

Data Index: 6660133 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.7428. Min Act: -0.1700

Data Index: 1568672 (Open Web Text)

Max Activating Token Index: 877

Text #19

Max Range: 4.3381. Min Range: -4.3381

Max Act: 3.7015. Min Act: -0.1700

Data Index: 3165027 (Open Web Text)

Max Activating Token Index: 481