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

Dataset: Open Web Text

Neuron 2148 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: 2.6607. Min Range: -2.6607

Max Act: 2.6607. Min Act: -0.1700

Data Index: 5734196 (Open Web Text)

Max Activating Token Index: 841

Text #1

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.6398. Min Act: -0.1700

Data Index: 8222690 (Open Web Text)

Max Activating Token Index: 135

Text #2

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.6281. Min Act: -0.1700

Data Index: 1008280 (Open Web Text)

Max Activating Token Index: 237

Text #3

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5918. Min Act: -0.1700

Data Index: 3820368 (Open Web Text)

Max Activating Token Index: 980

Text #4

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5951. Min Act: -0.1700

Data Index: 6949862 (Open Web Text)

Max Activating Token Index: 491

Text #5

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5817. Min Act: -0.1700

Data Index: 92009 (Open Web Text)

Max Activating Token Index: 37

Text #6

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5799. Min Act: -0.1700

Data Index: 5390225 (Open Web Text)

Max Activating Token Index: 375

Text #7

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5698. Min Act: -0.1700

Data Index: 4671152 (Open Web Text)

Max Activating Token Index: 259

Text #8

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5629. Min Act: -0.1700

Data Index: 7956899 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5134. Min Act: -0.1700

Data Index: 1904807 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5214. Min Act: -0.1700

Data Index: 92008 (Open Web Text)

Max Activating Token Index: 822

Text #11

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5117. Min Act: -0.1700

Data Index: 783574 (Open Web Text)

Max Activating Token Index: 503

Text #12

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5183. Min Act: -0.1700

Data Index: 7362124 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5053. Min Act: -0.1700

Data Index: 8318800 (Open Web Text)

Max Activating Token Index: 927

Text #14

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5203. Min Act: -0.1700

Data Index: 3178614 (Open Web Text)

Max Activating Token Index: 470

Text #15

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.4890. Min Act: -0.1700

Data Index: 8005255 (Open Web Text)

Max Activating Token Index: 739

Text #16

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5019. Min Act: -0.1700

Data Index: 6598846 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.5112. Min Act: -0.1700

Data Index: 209407 (Open Web Text)

Max Activating Token Index: 59

Text #18

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.4985. Min Act: -0.1700

Data Index: 8154156 (Open Web Text)

Max Activating Token Index: 419

Text #19

Max Range: 2.6607. Min Range: -2.6607

Max Act: 2.4968. Min Act: -0.1700

Data Index: 4673713 (Open Web Text)

Max Activating Token Index: 2