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

Dataset: Open Web Text

Neuron 3046 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: 3.1878. Min Range: -3.1878

Max Act: 3.1878. Min Act: -0.1700

Data Index: 7449341 (Open Web Text)

Max Activating Token Index: 681

Text #1

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.1590. Min Act: -0.1700

Data Index: 8709234 (Open Web Text)

Max Activating Token Index: 893

Text #2

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.1121. Min Act: -0.1700

Data Index: 5093689 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.1110. Min Act: -0.1700

Data Index: 5725623 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.1112. Min Act: -0.1700

Data Index: 1712970 (Open Web Text)

Max Activating Token Index: 799

Text #5

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.1025. Min Act: -0.1700

Data Index: 5212983 (Open Web Text)

Max Activating Token Index: 336

Text #6

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.1232. Min Act: -0.1700

Data Index: 2042082 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.0674. Min Act: -0.1700

Data Index: 8269945 (Open Web Text)

Max Activating Token Index: 60

Text #8

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.0800. Min Act: -0.1700

Data Index: 181847 (Open Web Text)

Max Activating Token Index: 639

Text #9

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.0715. Min Act: -0.1700

Data Index: 6764374 (Open Web Text)

Max Activating Token Index: 210

Text #10

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.0157. Min Act: -0.1700

Data Index: 7277269 (Open Web Text)

Max Activating Token Index: 726

Text #11

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.0689. Min Act: -0.1700

Data Index: 5426672 (Open Web Text)

Max Activating Token Index: 728

Text #12

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.0298. Min Act: -0.1700

Data Index: 201340 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 3.1878. Min Range: -3.1878

Max Act: 3.0112. Min Act: -0.1700

Data Index: 4192178 (Open Web Text)

Max Activating Token Index: 345

Text #14

Max Range: 3.1878. Min Range: -3.1878

Max Act: 2.9926. Min Act: -0.1700

Data Index: 7051806 (Open Web Text)

Max Activating Token Index: 710

Text #15

Max Range: 3.1878. Min Range: -3.1878

Max Act: 2.9879. Min Act: -0.1700

Data Index: 5131019 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 3.1878. Min Range: -3.1878

Max Act: 2.9973. Min Act: -0.1700

Data Index: 1051201 (Open Web Text)

Max Activating Token Index: 800

Text #17

Max Range: 3.1878. Min Range: -3.1878

Max Act: 2.9807. Min Act: -0.1700

Data Index: 7794705 (Open Web Text)

Max Activating Token Index: 193

Text #18

Max Range: 3.1878. Min Range: -3.1878

Max Act: 2.9889. Min Act: -0.1700

Data Index: 5467327 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 3.1878. Min Range: -3.1878

Max Act: 2.9935. Min Act: -0.1700

Data Index: 5467328 (Open Web Text)

Max Activating Token Index: 722