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

Dataset: Open Web Text

Neuron 2844 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: 4.1046. Min Range: -4.1046

Max Act: 4.0724. Min Act: -0.1700

Data Index: 655833 (Open Web Text)

Max Activating Token Index: 512

Text #1

Max Range: 4.1046. Min Range: -4.1046

Max Act: 4.1046. Min Act: -0.1700

Data Index: 1872960 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.1046. Min Range: -4.1046

Max Act: 4.0675. Min Act: -0.1700

Data Index: 3390209 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 4.1046. Min Range: -4.1046

Max Act: 4.0289. Min Act: -0.1700

Data Index: 3928624 (Open Web Text)

Max Activating Token Index: 791

Text #4

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9751. Min Act: -0.1700

Data Index: 8577571 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9364. Min Act: -0.1700

Data Index: 3217298 (Open Web Text)

Max Activating Token Index: 805

Text #6

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9327. Min Act: -0.1700

Data Index: 8736956 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9593. Min Act: -0.1700

Data Index: 944846 (Open Web Text)

Max Activating Token Index: 579

Text #8

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.8971. Min Act: -0.1700

Data Index: 2817162 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9250. Min Act: -0.1700

Data Index: 5070123 (Open Web Text)

Max Activating Token Index: 443

Text #10

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9087. Min Act: -0.1700

Data Index: 5115079 (Open Web Text)

Max Activating Token Index: 988

Text #11

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9235. Min Act: -0.1700

Data Index: 1593043 (Open Web Text)

Max Activating Token Index: 665

Text #12

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9437. Min Act: -0.1700

Data Index: 3068486 (Open Web Text)

Max Activating Token Index: 766

Text #13

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.8958. Min Act: -0.1700

Data Index: 5141623 (Open Web Text)

Max Activating Token Index: 200

Text #14

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9102. Min Act: -0.1700

Data Index: 6262453 (Open Web Text)

Max Activating Token Index: 449

Text #15

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9203. Min Act: -0.1700

Data Index: 34963 (Open Web Text)

Max Activating Token Index: 718

Text #16

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9078. Min Act: -0.1700

Data Index: 2640803 (Open Web Text)

Max Activating Token Index: 982

Text #17

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9057. Min Act: -0.1700

Data Index: 6841920 (Open Web Text)

Max Activating Token Index: 728

Text #18

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9318. Min Act: -0.1700

Data Index: 7109648 (Open Web Text)

Max Activating Token Index: 1016

Text #19

Max Range: 4.1046. Min Range: -4.1046

Max Act: 3.9052. Min Act: -0.1700

Data Index: 7894033 (Open Web Text)

Max Activating Token Index: 973