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

Dataset: Open Web Text

Neuron 2699 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: 4.0631. Min Range: -4.0631

Max Act: 4.0631. Min Act: -0.1700

Data Index: 2307277 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.9535. Min Act: -0.1700

Data Index: 5062007 (Open Web Text)

Max Activating Token Index: 718

Text #2

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.9875. Min Act: -0.1700

Data Index: 84464 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.9523. Min Act: -0.1700

Data Index: 5671231 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8584. Min Act: -0.1700

Data Index: 5964526 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8503. Min Act: -0.1700

Data Index: 230078 (Open Web Text)

Max Activating Token Index: 403

Text #6

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8135. Min Act: -0.1700

Data Index: 7959535 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8535. Min Act: -0.1700

Data Index: 1005827 (Open Web Text)

Max Activating Token Index: 172

Text #8

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.7693. Min Act: -0.1700

Data Index: 4687630 (Open Web Text)

Max Activating Token Index: 648

Text #9

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8333. Min Act: -0.1700

Data Index: 7198300 (Open Web Text)

Max Activating Token Index: 389

Text #10

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8365. Min Act: -0.1700

Data Index: 5194558 (Open Web Text)

Max Activating Token Index: 250

Text #11

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8776. Min Act: -0.1700

Data Index: 7039874 (Open Web Text)

Max Activating Token Index: 396

Text #12

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8384. Min Act: -0.1700

Data Index: 1291393 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.7877. Min Act: -0.1700

Data Index: 772215 (Open Web Text)

Max Activating Token Index: 466

Text #14

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8129. Min Act: -0.1700

Data Index: 8148156 (Open Web Text)

Max Activating Token Index: 818

Text #15

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.7987. Min Act: -0.1700

Data Index: 8037475 (Open Web Text)

Max Activating Token Index: 683

Text #16

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.7808. Min Act: -0.1700

Data Index: 1728977 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.8020. Min Act: -0.1700

Data Index: 2599461 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.7752. Min Act: -0.1700

Data Index: 7490548 (Open Web Text)

Max Activating Token Index: 335

Text #19

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.7604. Min Act: -0.1700

Data Index: 668712 (Open Web Text)

Max Activating Token Index: 365