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

Dataset: Open Web Text

Neuron 1064 in Layer 4

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: 3.9746. Min Range: -3.9746

Max Act: 3.9746. Min Act: -0.1700

Data Index: 1041647 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9474. Min Act: -0.1700

Data Index: 2851119 (Open Web Text)

Max Activating Token Index: 832

Text #2

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9205. Min Act: -0.1700

Data Index: 3823095 (Open Web Text)

Max Activating Token Index: 867

Text #3

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9215. Min Act: -0.1700

Data Index: 8539396 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9023. Min Act: -0.1700

Data Index: 7780632 (Open Web Text)

Max Activating Token Index: 776

Text #5

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9057. Min Act: -0.1700

Data Index: 6845114 (Open Web Text)

Max Activating Token Index: 703

Text #6

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9010. Min Act: -0.1700

Data Index: 6540895 (Open Web Text)

Max Activating Token Index: 786

Text #7

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9351. Min Act: -0.1700

Data Index: 6265315 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9296. Min Act: -0.1700

Data Index: 5414721 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9074. Min Act: -0.1700

Data Index: 5198755 (Open Web Text)

Max Activating Token Index: 810

Text #10

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9311. Min Act: -0.1700

Data Index: 5009889 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9224. Min Act: -0.1700

Data Index: 3921971 (Open Web Text)

Max Activating Token Index: 832

Text #12

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.8959. Min Act: -0.1700

Data Index: 83484 (Open Web Text)

Max Activating Token Index: 861

Text #13

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.8910. Min Act: -0.1700

Data Index: 2995128 (Open Web Text)

Max Activating Token Index: 805

Text #14

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9068. Min Act: -0.1700

Data Index: 113231 (Open Web Text)

Max Activating Token Index: 728

Text #15

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9036. Min Act: -0.1700

Data Index: 1105583 (Open Web Text)

Max Activating Token Index: 581

Text #16

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9318. Min Act: -0.1700

Data Index: 639943 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.8965. Min Act: -0.1700

Data Index: 2591153 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9135. Min Act: -0.1700

Data Index: 2332814 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 3.9746. Min Range: -3.9746

Max Act: 3.9177. Min Act: -0.1700

Data Index: 988136 (Open Web Text)

Max Activating Token Index: 622