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

Dataset: Open Web Text

Neuron 1837 in Layer 2

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: 4.7702. Min Range: -4.7702

Max Act: 4.7702. Min Act: -0.1700

Data Index: 8661413 (Open Web Text)

Max Activating Token Index: 314

Text #1

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.7558. Min Act: -0.1700

Data Index: 1746838 (Open Web Text)

Max Activating Token Index: 286

Text #2

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6961. Min Act: -0.1700

Data Index: 898133 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.7145. Min Act: -0.1700

Data Index: 8661404 (Open Web Text)

Max Activating Token Index: 549

Text #4

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.7059. Min Act: -0.1700

Data Index: 5284878 (Open Web Text)

Max Activating Token Index: 151

Text #5

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.7076. Min Act: -0.1700

Data Index: 429058 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.7219. Min Act: -0.1700

Data Index: 6754389 (Open Web Text)

Max Activating Token Index: 486

Text #7

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.7158. Min Act: -0.1700

Data Index: 2045926 (Open Web Text)

Max Activating Token Index: 782

Text #8

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.7072. Min Act: -0.1700

Data Index: 5972534 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6632. Min Act: -0.1700

Data Index: 7980753 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6923. Min Act: -0.1700

Data Index: 3353991 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6664. Min Act: -0.1700

Data Index: 5385387 (Open Web Text)

Max Activating Token Index: 910

Text #12

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6880. Min Act: -0.1700

Data Index: 8388041 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6388. Min Act: -0.1700

Data Index: 6604857 (Open Web Text)

Max Activating Token Index: 674

Text #14

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6480. Min Act: -0.1700

Data Index: 2687345 (Open Web Text)

Max Activating Token Index: 593

Text #15

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6513. Min Act: -0.1700

Data Index: 1312704 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6423. Min Act: -0.1700

Data Index: 5348699 (Open Web Text)

Max Activating Token Index: 27

Text #17

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6724. Min Act: -0.1700

Data Index: 3242731 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6578. Min Act: -0.1700

Data Index: 7110572 (Open Web Text)

Max Activating Token Index: 158

Text #19

Max Range: 4.7702. Min Range: -4.7702

Max Act: 4.6470. Min Act: -0.1700

Data Index: 7960496 (Open Web Text)

Max Activating Token Index: 401