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

Dataset: Open Web Text

Neuron 950 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: 2.5432. Min Range: -2.5432

Max Act: 2.5104. Min Act: -0.1700

Data Index: 2591286 (Open Web Text)

Max Activating Token Index: 159

Text #1

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.5305. Min Act: -0.1700

Data Index: 6492717 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.5432. Min Act: -0.1700

Data Index: 5761339 (Open Web Text)

Max Activating Token Index: 803

Text #3

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.5108. Min Act: -0.1700

Data Index: 327978 (Open Web Text)

Max Activating Token Index: 750

Text #4

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.4935. Min Act: -0.1700

Data Index: 1351825 (Open Web Text)

Max Activating Token Index: 729

Text #5

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.4990. Min Act: -0.1700

Data Index: 4869712 (Open Web Text)

Max Activating Token Index: 515

Text #6

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.4831. Min Act: -0.1700

Data Index: 8010927 (Open Web Text)

Max Activating Token Index: 195

Text #7

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.5031. Min Act: -0.1700

Data Index: 4330826 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.4811. Min Act: -0.1700

Data Index: 104713 (Open Web Text)

Max Activating Token Index: 835

Text #9

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.4313. Min Act: -0.1700

Data Index: 480986 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.4275. Min Act: -0.1700

Data Index: 5803739 (Open Web Text)

Max Activating Token Index: 887

Text #11

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3924. Min Act: -0.1700

Data Index: 6239941 (Open Web Text)

Max Activating Token Index: 757

Text #12

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3862. Min Act: -0.1700

Data Index: 2842590 (Open Web Text)

Max Activating Token Index: 92

Text #13

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3878. Min Act: -0.1700

Data Index: 2935918 (Open Web Text)

Max Activating Token Index: 561

Text #14

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3982. Min Act: -0.1700

Data Index: 4600660 (Open Web Text)

Max Activating Token Index: 74

Text #15

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3992. Min Act: -0.1700

Data Index: 7020918 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3807. Min Act: -0.1700

Data Index: 6918826 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3655. Min Act: -0.1700

Data Index: 7391364 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3718. Min Act: -0.1700

Data Index: 7496046 (Open Web Text)

Max Activating Token Index: 766

Text #19

Max Range: 2.5432. Min Range: -2.5432

Max Act: 2.3665. Min Act: -0.1700

Data Index: 3122466 (Open Web Text)

Max Activating Token Index: 695