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

Dataset: Open Web Text

Neuron 1451 in Layer 6

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: 7.3159. Min Range: -7.3159

Max Act: 7.3159. Min Act: -0.1700

Data Index: 3158279 (Open Web Text)

Max Activating Token Index: 804

Text #1

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.8613. Min Act: -0.1700

Data Index: 2071898 (Open Web Text)

Max Activating Token Index: 604

Text #2

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.7891. Min Act: -0.1700

Data Index: 7102328 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.6969. Min Act: -0.1700

Data Index: 8270062 (Open Web Text)

Max Activating Token Index: 867

Text #4

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.6155. Min Act: -0.1700

Data Index: 1127147 (Open Web Text)

Max Activating Token Index: 852

Text #5

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.6232. Min Act: -0.1700

Data Index: 7524621 (Open Web Text)

Max Activating Token Index: 907

Text #6

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.5631. Min Act: -0.1700

Data Index: 1749758 (Open Web Text)

Max Activating Token Index: 791

Text #7

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.5383. Min Act: -0.1700

Data Index: 3809319 (Open Web Text)

Max Activating Token Index: 751

Text #8

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.5343. Min Act: -0.1700

Data Index: 7682867 (Open Web Text)

Max Activating Token Index: 921

Text #9

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.4813. Min Act: -0.1700

Data Index: 8240631 (Open Web Text)

Max Activating Token Index: 999

Text #10

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.5031. Min Act: -0.1700

Data Index: 701509 (Open Web Text)

Max Activating Token Index: 932

Text #11

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.4776. Min Act: -0.1700

Data Index: 771222 (Open Web Text)

Max Activating Token Index: 694

Text #12

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.4856. Min Act: -0.1700

Data Index: 8600121 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.4423. Min Act: -0.1700

Data Index: 6034769 (Open Web Text)

Max Activating Token Index: 744

Text #14

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.4256. Min Act: -0.1700

Data Index: 597621 (Open Web Text)

Max Activating Token Index: 940

Text #15

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.3851. Min Act: -0.1700

Data Index: 6865494 (Open Web Text)

Max Activating Token Index: 618

Text #16

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.3977. Min Act: -0.1700

Data Index: 4798027 (Open Web Text)

Max Activating Token Index: 1000

Text #17

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.4069. Min Act: -0.1700

Data Index: 7497876 (Open Web Text)

Max Activating Token Index: 885

Text #18

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.4374. Min Act: -0.1700

Data Index: 7142877 (Open Web Text)

Max Activating Token Index: 808

Text #19

Max Range: 7.3159. Min Range: -7.3159

Max Act: 6.5415. Min Act: -0.1700

Data Index: 2398604 (Open Web Text)

Max Activating Token Index: 857