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

Dataset: Open Web Text

Neuron 104 in Layer 3

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: 3.8828. Min Range: -3.8828

Max Act: 3.8828. Min Act: -0.1700

Data Index: 4610035 (Open Web Text)

Max Activating Token Index: 225

Text #1

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.8336. Min Act: -0.1700

Data Index: 1873006 (Open Web Text)

Max Activating Token Index: 625

Text #2

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.8002. Min Act: -0.1700

Data Index: 5207624 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.8137. Min Act: -0.1700

Data Index: 1771578 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.8041. Min Act: -0.1700

Data Index: 8324617 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7659. Min Act: -0.1700

Data Index: 3954920 (Open Web Text)

Max Activating Token Index: 845

Text #6

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7492. Min Act: -0.1700

Data Index: 8204801 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6910. Min Act: -0.1700

Data Index: 3117180 (Open Web Text)

Max Activating Token Index: 393

Text #8

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6900. Min Act: -0.1700

Data Index: 5156883 (Open Web Text)

Max Activating Token Index: 448

Text #9

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6921. Min Act: -0.1700

Data Index: 505445 (Open Web Text)

Max Activating Token Index: 955

Text #10

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6581. Min Act: -0.1700

Data Index: 3118987 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6744. Min Act: -0.1700

Data Index: 3392956 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6813. Min Act: -0.1700

Data Index: 5150402 (Open Web Text)

Max Activating Token Index: 872

Text #13

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6911. Min Act: -0.1700

Data Index: 214722 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6875. Min Act: -0.1700

Data Index: 4016051 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6724. Min Act: -0.1700

Data Index: 5538182 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6987. Min Act: -0.1700

Data Index: 5969003 (Open Web Text)

Max Activating Token Index: 768

Text #17

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6271. Min Act: -0.1700

Data Index: 437622 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6293. Min Act: -0.1700

Data Index: 3972293 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6311. Min Act: -0.1700

Data Index: 5993983 (Open Web Text)

Max Activating Token Index: 672