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

Dataset: Open Web Text

Neuron 609 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: 4.3801. Min Range: -4.3801

Max Act: 4.3683. Min Act: -0.1700

Data Index: 7226739 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.3652. Min Act: -0.1700

Data Index: 4702834 (Open Web Text)

Max Activating Token Index: 200

Text #2

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.3801. Min Act: -0.1700

Data Index: 5415645 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.3075. Min Act: -0.1700

Data Index: 4518307 (Open Web Text)

Max Activating Token Index: 879

Text #4

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2921. Min Act: -0.1700

Data Index: 221734 (Open Web Text)

Max Activating Token Index: 484

Text #5

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.3010. Min Act: -0.1700

Data Index: 4023559 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2715. Min Act: -0.1700

Data Index: 7930022 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2196. Min Act: -0.1700

Data Index: 987880 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2437. Min Act: -0.1700

Data Index: 7143994 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2477. Min Act: -0.1700

Data Index: 2906905 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2455. Min Act: -0.1700

Data Index: 7380741 (Open Web Text)

Max Activating Token Index: 866

Text #11

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2232. Min Act: -0.1700

Data Index: 3490438 (Open Web Text)

Max Activating Token Index: 581

Text #12

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2266. Min Act: -0.1700

Data Index: 7380742 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2019. Min Act: -0.1700

Data Index: 2376480 (Open Web Text)

Max Activating Token Index: 273

Text #14

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1921. Min Act: -0.1700

Data Index: 6141784 (Open Web Text)

Max Activating Token Index: 475

Text #15

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1890. Min Act: -0.1700

Data Index: 5975415 (Open Web Text)

Max Activating Token Index: 232

Text #16

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2007. Min Act: -0.1700

Data Index: 4877820 (Open Web Text)

Max Activating Token Index: 882

Text #17

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2070. Min Act: -0.1700

Data Index: 1640490 (Open Web Text)

Max Activating Token Index: 687

Text #18

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1809. Min Act: -0.1700

Data Index: 8251739 (Open Web Text)

Max Activating Token Index: 93

Text #19

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2051. Min Act: -0.1700

Data Index: 5349638 (Open Web Text)

Max Activating Token Index: 638