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

Dataset: Open Web Text

Neuron 1363 in Layer 1

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: 4.9999. Min Range: -4.9999

Max Act: 4.9999. Min Act: -0.1700

Data Index: 1477653 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9640. Min Act: -0.1700

Data Index: 3615281 (Open Web Text)

Max Activating Token Index: 380

Text #2

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9309. Min Act: -0.1700

Data Index: 6260775 (Open Web Text)

Max Activating Token Index: 29

Text #3

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9082. Min Act: -0.1700

Data Index: 1235421 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8965. Min Act: -0.1700

Data Index: 1956269 (Open Web Text)

Max Activating Token Index: 996

Text #5

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9019. Min Act: -0.1700

Data Index: 1872754 (Open Web Text)

Max Activating Token Index: 373

Text #6

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9036. Min Act: -0.1700

Data Index: 8403378 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9182. Min Act: -0.1700

Data Index: 51478 (Open Web Text)

Max Activating Token Index: 604

Text #8

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9098. Min Act: -0.1700

Data Index: 8115780 (Open Web Text)

Max Activating Token Index: 375

Text #9

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9081. Min Act: -0.1700

Data Index: 7060647 (Open Web Text)

Max Activating Token Index: 254

Text #10

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8768. Min Act: -0.1700

Data Index: 4107273 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8819. Min Act: -0.1700

Data Index: 1757006 (Open Web Text)

Max Activating Token Index: 348

Text #12

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8640. Min Act: -0.1700

Data Index: 2251402 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8835. Min Act: -0.1700

Data Index: 4732070 (Open Web Text)

Max Activating Token Index: 247

Text #14

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.9039. Min Act: -0.1700

Data Index: 5697507 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8941. Min Act: -0.1700

Data Index: 504105 (Open Web Text)

Max Activating Token Index: 752

Text #16

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8794. Min Act: -0.1700

Data Index: 815494 (Open Web Text)

Max Activating Token Index: 963

Text #17

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8781. Min Act: -0.1700

Data Index: 2296038 (Open Web Text)

Max Activating Token Index: 621

Text #18

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8788. Min Act: -0.1700

Data Index: 2517290 (Open Web Text)

Max Activating Token Index: 320

Text #19

Max Range: 4.9999. Min Range: -4.9999

Max Act: 4.8750. Min Act: -0.1700

Data Index: 6256326 (Open Web Text)

Max Activating Token Index: 891