Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 4091 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 7.1016. Min Range: -7.1016

Max Act: 7.1016. Min Act: -0.1700

Data Index: 5805189 (Open Web Text)

Max Activating Token Index: 895

Text #1

Max Range: 7.1016. Min Range: -7.1016

Max Act: 7.0391. Min Act: -0.1700

Data Index: 2222621 (Open Web Text)

Max Activating Token Index: 950

Text #2

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9141. Min Act: -0.1700

Data Index: 34311 (Open Web Text)

Max Activating Token Index: 747

Text #3

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9766. Min Act: -0.1700

Data Index: 846087 (Open Web Text)

Max Activating Token Index: 804

Text #4

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9141. Min Act: -0.1700

Data Index: 2205447 (Open Web Text)

Max Activating Token Index: 742

Text #5

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9141. Min Act: -0.1700

Data Index: 4141409 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9453. Min Act: -0.1700

Data Index: 4338223 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8203. Min Act: -0.1700

Data Index: 7335045 (Open Web Text)

Max Activating Token Index: 866

Text #8

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9141. Min Act: -0.1700

Data Index: 1558305 (Open Web Text)

Max Activating Token Index: 809

Text #9

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7578. Min Act: -0.1700

Data Index: 7089951 (Open Web Text)

Max Activating Token Index: 879

Text #10

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8516. Min Act: -0.1700

Data Index: 8123639 (Open Web Text)

Max Activating Token Index: 875

Text #11

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8203. Min Act: -0.1700

Data Index: 2593782 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8828. Min Act: -0.1700

Data Index: 5504267 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9453. Min Act: -0.1700

Data Index: 630182 (Open Web Text)

Max Activating Token Index: 925

Text #14

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8828. Min Act: -0.1700

Data Index: 6304395 (Open Web Text)

Max Activating Token Index: 867

Text #15

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8203. Min Act: -0.1700

Data Index: 5484492 (Open Web Text)

Max Activating Token Index: 955

Text #16

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8203. Min Act: -0.1700

Data Index: 3911991 (Open Web Text)

Max Activating Token Index: 629

Text #17

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8516. Min Act: -0.1700

Data Index: 4494939 (Open Web Text)

Max Activating Token Index: 841

Text #18

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7891. Min Act: -0.1700

Data Index: 3499034 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8203. Min Act: -0.1700

Data Index: 1456167 (Open Web Text)

Max Activating Token Index: 593