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

Dataset: Open Web Text

Neuron 377 in Layer 6

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: 3.4010. Min Range: -3.4010

Max Act: 3.4010. Min Act: -0.1700

Data Index: 4678356 (Open Web Text)

Max Activating Token Index: 977

Text #1

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.2318. Min Act: -0.1700

Data Index: 8106613 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.1933. Min Act: -0.1700

Data Index: 1604852 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.2053. Min Act: -0.1700

Data Index: 5050867 (Open Web Text)

Max Activating Token Index: 107

Text #4

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.1734. Min Act: -0.1700

Data Index: 336182 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.1779. Min Act: -0.1700

Data Index: 3502948 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.1344. Min Act: -0.1700

Data Index: 5698365 (Open Web Text)

Max Activating Token Index: 300

Text #7

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.1257. Min Act: -0.1700

Data Index: 1987718 (Open Web Text)

Max Activating Token Index: 720

Text #8

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.1185. Min Act: -0.1700

Data Index: 3528097 (Open Web Text)

Max Activating Token Index: 600

Text #9

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0692. Min Act: -0.1700

Data Index: 291344 (Open Web Text)

Max Activating Token Index: 555

Text #10

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0753. Min Act: -0.1700

Data Index: 7504233 (Open Web Text)

Max Activating Token Index: 745

Text #11

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0759. Min Act: -0.1700

Data Index: 642962 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0825. Min Act: -0.1700

Data Index: 4251857 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.1024. Min Act: -0.1700

Data Index: 3513856 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0418. Min Act: -0.1700

Data Index: 3888113 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0344. Min Act: -0.1700

Data Index: 6999071 (Open Web Text)

Max Activating Token Index: 852

Text #16

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0628. Min Act: -0.1700

Data Index: 7514941 (Open Web Text)

Max Activating Token Index: 825

Text #17

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0681. Min Act: -0.1700

Data Index: 8831719 (Open Web Text)

Max Activating Token Index: 697

Text #18

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0519. Min Act: -0.1700

Data Index: 3654559 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 3.4010. Min Range: -3.4010

Max Act: 3.0359. Min Act: -0.1700

Data Index: 5484582 (Open Web Text)

Max Activating Token Index: 637