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

Dataset: Open Web Text

Neuron 603 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: 4.7718. Min Range: -4.7718

Max Act: 4.7718. Min Act: -0.1700

Data Index: 2726410 (Open Web Text)

Max Activating Token Index: 124

Text #1

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6744. Min Act: -0.1700

Data Index: 7163198 (Open Web Text)

Max Activating Token Index: 327

Text #2

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6346. Min Act: -0.1700

Data Index: 7123993 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6908. Min Act: -0.1700

Data Index: 7472056 (Open Web Text)

Max Activating Token Index: 176

Text #4

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6633. Min Act: -0.1700

Data Index: 817307 (Open Web Text)

Max Activating Token Index: 424

Text #5

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6540. Min Act: -0.1700

Data Index: 2106465 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6297. Min Act: -0.1700

Data Index: 1320673 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6382. Min Act: -0.1700

Data Index: 2419476 (Open Web Text)

Max Activating Token Index: 78

Text #8

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6129. Min Act: -0.1700

Data Index: 3924530 (Open Web Text)

Max Activating Token Index: 978

Text #9

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.6151. Min Act: -0.1700

Data Index: 608510 (Open Web Text)

Max Activating Token Index: 120

Text #10

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.5736. Min Act: -0.1700

Data Index: 6255432 (Open Web Text)

Max Activating Token Index: 703

Text #11

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.5606. Min Act: -0.1700

Data Index: 7820504 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.4859. Min Act: -0.1700

Data Index: 6437640 (Open Web Text)

Max Activating Token Index: 856

Text #13

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.5648. Min Act: -0.1700

Data Index: 5367550 (Open Web Text)

Max Activating Token Index: 443

Text #14

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.4833. Min Act: -0.1700

Data Index: 4071009 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.4269. Min Act: -0.1700

Data Index: 560528 (Open Web Text)

Max Activating Token Index: 767

Text #16

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.4105. Min Act: -0.1700

Data Index: 7928150 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.4262. Min Act: -0.1700

Data Index: 7212237 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.4268. Min Act: -0.1700

Data Index: 5498514 (Open Web Text)

Max Activating Token Index: 889

Text #19

Max Range: 4.7718. Min Range: -4.7718

Max Act: 4.4034. Min Act: -0.1700

Data Index: 3373280 (Open Web Text)

Max Activating Token Index: 717