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

Dataset: Open Web Text

Neuron 643 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: 4.4573. Min Range: -4.4573

Max Act: 4.4426. Min Act: -0.1700

Data Index: 8240286 (Open Web Text)

Max Activating Token Index: 668

Text #1

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.4051. Min Act: -0.1700

Data Index: 2710455 (Open Web Text)

Max Activating Token Index: 783

Text #2

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.4573. Min Act: -0.1700

Data Index: 5031454 (Open Web Text)

Max Activating Token Index: 486

Text #3

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.3849. Min Act: -0.1700

Data Index: 4385916 (Open Web Text)

Max Activating Token Index: 471

Text #4

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.3633. Min Act: -0.1700

Data Index: 8774532 (Open Web Text)

Max Activating Token Index: 408

Text #5

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.3070. Min Act: -0.1700

Data Index: 3657949 (Open Web Text)

Max Activating Token Index: 234

Text #6

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.3710. Min Act: -0.1700

Data Index: 3393100 (Open Web Text)

Max Activating Token Index: 779

Text #7

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2875. Min Act: -0.1700

Data Index: 7431671 (Open Web Text)

Max Activating Token Index: 530

Text #8

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2975. Min Act: -0.1700

Data Index: 6953007 (Open Web Text)

Max Activating Token Index: 217

Text #9

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.3263. Min Act: -0.1700

Data Index: 2785773 (Open Web Text)

Max Activating Token Index: 496

Text #10

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.3800. Min Act: -0.1700

Data Index: 3577466 (Open Web Text)

Max Activating Token Index: 836

Text #11

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2699. Min Act: -0.1700

Data Index: 2348637 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2863. Min Act: -0.1700

Data Index: 3925192 (Open Web Text)

Max Activating Token Index: 495

Text #13

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2953. Min Act: -0.1700

Data Index: 2212429 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2867. Min Act: -0.1700

Data Index: 3030142 (Open Web Text)

Max Activating Token Index: 614

Text #15

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2933. Min Act: -0.1700

Data Index: 5833082 (Open Web Text)

Max Activating Token Index: 203

Text #16

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2734. Min Act: -0.1700

Data Index: 5561338 (Open Web Text)

Max Activating Token Index: 33

Text #17

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2335. Min Act: -0.1700

Data Index: 5168989 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2355. Min Act: -0.1700

Data Index: 2012014 (Open Web Text)

Max Activating Token Index: 554

Text #19

Max Range: 4.4573. Min Range: -4.4573

Max Act: 4.2461. Min Act: -0.1700

Data Index: 6911195 (Open Web Text)

Max Activating Token Index: 434