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

Dataset: Open Web Text

Neuron 518 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: 3.3713. Min Range: -3.3713

Max Act: 3.3713. Min Act: -0.1700

Data Index: 6170829 (Open Web Text)

Max Activating Token Index: 340

Text #1

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3369. Min Act: -0.1700

Data Index: 594687 (Open Web Text)

Max Activating Token Index: 593

Text #2

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3665. Min Act: -0.1700

Data Index: 3973891 (Open Web Text)

Max Activating Token Index: 504

Text #3

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3596. Min Act: -0.1700

Data Index: 525585 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3120. Min Act: -0.1700

Data Index: 7541124 (Open Web Text)

Max Activating Token Index: 812

Text #5

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3050. Min Act: -0.1700

Data Index: 6247969 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2941. Min Act: -0.1700

Data Index: 108327 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3006. Min Act: -0.1700

Data Index: 1531345 (Open Web Text)

Max Activating Token Index: 587

Text #8

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3152. Min Act: -0.1700

Data Index: 8003592 (Open Web Text)

Max Activating Token Index: 679

Text #9

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3074. Min Act: -0.1700

Data Index: 7722206 (Open Web Text)

Max Activating Token Index: 768

Text #10

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2943. Min Act: -0.1700

Data Index: 3034864 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.3072. Min Act: -0.1700

Data Index: 536332 (Open Web Text)

Max Activating Token Index: 763

Text #12

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2895. Min Act: -0.1700

Data Index: 5585071 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2986. Min Act: -0.1700

Data Index: 2901800 (Open Web Text)

Max Activating Token Index: 576

Text #14

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2920. Min Act: -0.1700

Data Index: 3945460 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2636. Min Act: -0.1700

Data Index: 6138859 (Open Web Text)

Max Activating Token Index: 94

Text #16

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2673. Min Act: -0.1700

Data Index: 2947544 (Open Web Text)

Max Activating Token Index: 53

Text #17

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2839. Min Act: -0.1700

Data Index: 7450429 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2799. Min Act: -0.1700

Data Index: 5358932 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 3.3713. Min Range: -3.3713

Max Act: 3.2046. Min Act: -0.1700

Data Index: 6938418 (Open Web Text)

Max Activating Token Index: 554