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

Dataset: Open Web Text

Neuron 2225 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: 1.8834. Min Range: -1.8834

Max Act: 1.8834. Min Act: -0.1700

Data Index: 4681615 (Open Web Text)

Max Activating Token Index: 841

Text #1

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8706. Min Act: -0.1700

Data Index: 3612786 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8676. Min Act: -0.1700

Data Index: 5449990 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8390. Min Act: -0.1700

Data Index: 2849751 (Open Web Text)

Max Activating Token Index: 469

Text #4

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8282. Min Act: -0.1700

Data Index: 8214925 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8142. Min Act: -0.1700

Data Index: 7065023 (Open Web Text)

Max Activating Token Index: 758

Text #6

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8078. Min Act: -0.1700

Data Index: 853703 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8139. Min Act: -0.1700

Data Index: 1214559 (Open Web Text)

Max Activating Token Index: 550

Text #8

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8077. Min Act: -0.1700

Data Index: 3308546 (Open Web Text)

Max Activating Token Index: 981

Text #9

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8076. Min Act: -0.1693

Data Index: 5724929 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.7999. Min Act: -0.1700

Data Index: 5846926 (Open Web Text)

Max Activating Token Index: 314

Text #11

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8004. Min Act: -0.1700

Data Index: 1181489 (Open Web Text)

Max Activating Token Index: 943

Text #12

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.7987. Min Act: -0.1700

Data Index: 7751521 (Open Web Text)

Max Activating Token Index: 724

Text #13

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.8013. Min Act: -0.1700

Data Index: 4482668 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.7990. Min Act: -0.1700

Data Index: 8537620 (Open Web Text)

Max Activating Token Index: 298

Text #15

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.7957. Min Act: -0.1700

Data Index: 3308547 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.7910. Min Act: -0.1700

Data Index: 2811341 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.7847. Min Act: -0.1700

Data Index: 954431 (Open Web Text)

Max Activating Token Index: 528

Text #18

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.7878. Min Act: -0.1700

Data Index: 7288108 (Open Web Text)

Max Activating Token Index: 603

Text #19

Max Range: 1.8834. Min Range: -1.8834

Max Act: 1.7937. Min Act: -0.1700

Data Index: 3400175 (Open Web Text)

Max Activating Token Index: 579