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

Dataset: Open Web Text

Neuron 969 in Layer 0

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: 3.1759. Min Range: -3.1759

Max Act: 3.1716. Min Act: -0.1700

Data Index: 1151248 (Open Web Text)

Max Activating Token Index: 72

Text #1

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.1511. Min Act: -0.1700

Data Index: 2255411 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.1759. Min Act: -0.1700

Data Index: 7833241 (Open Web Text)

Max Activating Token Index: 951

Text #3

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.1095. Min Act: -0.1700

Data Index: 2992893 (Open Web Text)

Max Activating Token Index: 530

Text #4

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.1184. Min Act: -0.1700

Data Index: 6574754 (Open Web Text)

Max Activating Token Index: 685

Text #5

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.1099. Min Act: -0.1700

Data Index: 1759685 (Open Web Text)

Max Activating Token Index: 858

Text #6

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.1055. Min Act: -0.1700

Data Index: 3502695 (Open Web Text)

Max Activating Token Index: 536

Text #7

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0928. Min Act: -0.1700

Data Index: 5161734 (Open Web Text)

Max Activating Token Index: 339

Text #8

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0871. Min Act: -0.1700

Data Index: 7644116 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0904. Min Act: -0.1700

Data Index: 651345 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0884. Min Act: -0.1700

Data Index: 1999620 (Open Web Text)

Max Activating Token Index: 281

Text #11

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0990. Min Act: -0.1700

Data Index: 1938920 (Open Web Text)

Max Activating Token Index: 738

Text #12

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0811. Min Act: -0.1700

Data Index: 6048143 (Open Web Text)

Max Activating Token Index: 285

Text #13

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0718. Min Act: -0.1700

Data Index: 4711036 (Open Web Text)

Max Activating Token Index: 759

Text #14

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0836. Min Act: -0.1700

Data Index: 7036103 (Open Web Text)

Max Activating Token Index: 586

Text #15

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0704. Min Act: -0.1700

Data Index: 4573794 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0698. Min Act: -0.1700

Data Index: 5359407 (Open Web Text)

Max Activating Token Index: 73

Text #17

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0722. Min Act: -0.1700

Data Index: 5788873 (Open Web Text)

Max Activating Token Index: 812

Text #18

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0745. Min Act: -0.1700

Data Index: 8683019 (Open Web Text)

Max Activating Token Index: 244

Text #19

Max Range: 3.1759. Min Range: -3.1759

Max Act: 3.0772. Min Act: -0.1700

Data Index: 4480640 (Open Web Text)

Max Activating Token Index: 574