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

Dataset: Open Web Text

Neuron 2774 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: 2.5825. Min Range: -2.5825

Max Act: 2.5825. Min Act: -0.1700

Data Index: 5510041 (Open Web Text)

Max Activating Token Index: 102

Text #1

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.5701. Min Act: -0.1700

Data Index: 6192721 (Open Web Text)

Max Activating Token Index: 657

Text #2

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.5305. Min Act: -0.1700

Data Index: 7586776 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.5433. Min Act: -0.1700

Data Index: 596363 (Open Web Text)

Max Activating Token Index: 234

Text #4

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.5357. Min Act: -0.1700

Data Index: 439431 (Open Web Text)

Max Activating Token Index: 879

Text #5

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.5028. Min Act: -0.1700

Data Index: 6933838 (Open Web Text)

Max Activating Token Index: 959

Text #6

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4846. Min Act: -0.1700

Data Index: 8631495 (Open Web Text)

Max Activating Token Index: 789

Text #7

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4958. Min Act: -0.1700

Data Index: 7762311 (Open Web Text)

Max Activating Token Index: 509

Text #8

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4895. Min Act: -0.1700

Data Index: 6406077 (Open Web Text)

Max Activating Token Index: 605

Text #9

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.5029. Min Act: -0.1700

Data Index: 6028880 (Open Web Text)

Max Activating Token Index: 776

Text #10

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4881. Min Act: -0.1700

Data Index: 929393 (Open Web Text)

Max Activating Token Index: 647

Text #11

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4884. Min Act: -0.1700

Data Index: 4294282 (Open Web Text)

Max Activating Token Index: 542

Text #12

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.5084. Min Act: -0.1700

Data Index: 7603068 (Open Web Text)

Max Activating Token Index: 690

Text #13

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4811. Min Act: -0.1700

Data Index: 6107430 (Open Web Text)

Max Activating Token Index: 106

Text #14

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4751. Min Act: -0.1700

Data Index: 7575047 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4864. Min Act: -0.1700

Data Index: 7452066 (Open Web Text)

Max Activating Token Index: 175

Text #16

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4815. Min Act: -0.1700

Data Index: 5159457 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4715. Min Act: -0.1700

Data Index: 7074098 (Open Web Text)

Max Activating Token Index: 898

Text #18

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4810. Min Act: -0.1700

Data Index: 3040368 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 2.5825. Min Range: -2.5825

Max Act: 2.4718. Min Act: -0.1700

Data Index: 6801641 (Open Web Text)

Max Activating Token Index: 845