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

Dataset: Open Web Text

Neuron 2005 in Layer 0

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: 1.6565. Min Range: -1.6565

Max Act: 1.6565. Min Act: -0.1700

Data Index: 5680427 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.4372. Min Act: -0.1700

Data Index: 7390175 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.4013. Min Act: -0.1700

Data Index: 4108864 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3941. Min Act: -0.1700

Data Index: 4092750 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3590. Min Act: -0.1700

Data Index: 4927350 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3650. Min Act: -0.1700

Data Index: 5346857 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3574. Min Act: -0.1700

Data Index: 7110505 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3576. Min Act: -0.1700

Data Index: 8263708 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3638. Min Act: -0.1700

Data Index: 6496516 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3519. Min Act: -0.1700

Data Index: 7956643 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3519. Min Act: -0.1700

Data Index: 2808271 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3473. Min Act: -0.1700

Data Index: 2279962 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3407. Min Act: -0.1700

Data Index: 3450000 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3332. Min Act: -0.1700

Data Index: 7999404 (Open Web Text)

Max Activating Token Index: 744

Text #14

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3087. Min Act: -0.1700

Data Index: 1331696 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3162. Min Act: -0.1700

Data Index: 3281808 (Open Web Text)

Max Activating Token Index: 655

Text #16

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3164. Min Act: -0.1700

Data Index: 8173272 (Open Web Text)

Max Activating Token Index: 866

Text #17

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3095. Min Act: -0.1700

Data Index: 1373290 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.3105. Min Act: -0.1700

Data Index: 8721993 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.6565. Min Range: -1.6565

Max Act: 1.2987. Min Act: -0.1700

Data Index: 4879574 (Open Web Text)

Max Activating Token Index: 1023