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

Dataset: Open Web Text

Neuron 1611 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: 3.6516. Min Range: -3.6516

Max Act: 3.6516. Min Act: -0.1700

Data Index: 7050099 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.5692. Min Act: -0.1700

Data Index: 1080182 (Open Web Text)

Max Activating Token Index: 183

Text #2

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.5404. Min Act: -0.1700

Data Index: 6692518 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.5250. Min Act: -0.1700

Data Index: 3322991 (Open Web Text)

Max Activating Token Index: 115

Text #4

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4971. Min Act: -0.1700

Data Index: 5810636 (Open Web Text)

Max Activating Token Index: 123

Text #5

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4654. Min Act: -0.1700

Data Index: 6766869 (Open Web Text)

Max Activating Token Index: 162

Text #6

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.5071. Min Act: -0.1700

Data Index: 873213 (Open Web Text)

Max Activating Token Index: 870

Text #7

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4631. Min Act: -0.1700

Data Index: 3392920 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.5109. Min Act: -0.1700

Data Index: 4730327 (Open Web Text)

Max Activating Token Index: 103

Text #9

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4625. Min Act: -0.1700

Data Index: 3902355 (Open Web Text)

Max Activating Token Index: 108

Text #10

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.5094. Min Act: -0.1700

Data Index: 2505404 (Open Web Text)

Max Activating Token Index: 773

Text #11

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4838. Min Act: -0.1700

Data Index: 8686109 (Open Web Text)

Max Activating Token Index: 802

Text #12

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4645. Min Act: -0.1700

Data Index: 8040210 (Open Web Text)

Max Activating Token Index: 365

Text #13

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4782. Min Act: -0.1700

Data Index: 7765805 (Open Web Text)

Max Activating Token Index: 952

Text #14

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4684. Min Act: -0.1700

Data Index: 743519 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4652. Min Act: -0.1700

Data Index: 3986471 (Open Web Text)

Max Activating Token Index: 771

Text #16

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4712. Min Act: -0.1700

Data Index: 4332765 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4250. Min Act: -0.1700

Data Index: 3048839 (Open Web Text)

Max Activating Token Index: 695

Text #18

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4579. Min Act: -0.1700

Data Index: 81704 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 3.6516. Min Range: -3.6516

Max Act: 3.4542. Min Act: -0.1700

Data Index: 4366310 (Open Web Text)

Max Activating Token Index: 931