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

Dataset: Open Web Text

Neuron 1907 in Layer 5

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: 3.2416. Min Range: -3.2416

Max Act: 3.2416. Min Act: -0.1700

Data Index: 4921785 (Open Web Text)

Max Activating Token Index: 718

Text #1

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.1624. Min Act: -0.1700

Data Index: 8779998 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.1434. Min Act: -0.1700

Data Index: 5766906 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0686. Min Act: -0.1700

Data Index: 4738999 (Open Web Text)

Max Activating Token Index: 1013

Text #4

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0646. Min Act: -0.1700

Data Index: 2393558 (Open Web Text)

Max Activating Token Index: 648

Text #5

Max Range: 3.2416. Min Range: -3.2416

Max Act: 3.0058. Min Act: -0.1700

Data Index: 5028301 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.9619. Min Act: -0.1700

Data Index: 6912020 (Open Web Text)

Max Activating Token Index: 739

Text #7

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.9456. Min Act: -0.1700

Data Index: 3030916 (Open Web Text)

Max Activating Token Index: 138

Text #8

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8849. Min Act: -0.1700

Data Index: 2783448 (Open Web Text)

Max Activating Token Index: 809

Text #9

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8726. Min Act: -0.1700

Data Index: 6516825 (Open Web Text)

Max Activating Token Index: 767

Text #10

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8917. Min Act: -0.1700

Data Index: 6669175 (Open Web Text)

Max Activating Token Index: 523

Text #11

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8918. Min Act: -0.1700

Data Index: 1388475 (Open Web Text)

Max Activating Token Index: 839

Text #12

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.9224. Min Act: -0.1700

Data Index: 4784930 (Open Web Text)

Max Activating Token Index: 745

Text #13

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.9062. Min Act: -0.1700

Data Index: 1640732 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8595. Min Act: -0.1700

Data Index: 8016929 (Open Web Text)

Max Activating Token Index: 788

Text #15

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8754. Min Act: -0.1700

Data Index: 706118 (Open Web Text)

Max Activating Token Index: 997

Text #16

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8868. Min Act: -0.1700

Data Index: 2707961 (Open Web Text)

Max Activating Token Index: 577

Text #17

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8576. Min Act: -0.1700

Data Index: 3991504 (Open Web Text)

Max Activating Token Index: 209

Text #18

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8470. Min Act: -0.1700

Data Index: 812956 (Open Web Text)

Max Activating Token Index: 496

Text #19

Max Range: 3.2416. Min Range: -3.2416

Max Act: 2.8301. Min Act: -0.1700

Data Index: 1140183 (Open Web Text)

Max Activating Token Index: 733