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

Dataset: Open Web Text

Neuron 306 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: 3.1984. Min Range: -3.1984

Max Act: 3.1984. Min Act: -0.1700

Data Index: 7324387 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 3.1984. Min Range: -3.1984

Max Act: 3.1933. Min Act: -0.1700

Data Index: 4901418 (Open Web Text)

Max Activating Token Index: 727

Text #2

Max Range: 3.1984. Min Range: -3.1984

Max Act: 3.0798. Min Act: -0.1700

Data Index: 3517575 (Open Web Text)

Max Activating Token Index: 670

Text #3

Max Range: 3.1984. Min Range: -3.1984

Max Act: 3.0522. Min Act: -0.1700

Data Index: 234500 (Open Web Text)

Max Activating Token Index: 329

Text #4

Max Range: 3.1984. Min Range: -3.1984

Max Act: 3.0579. Min Act: -0.1700

Data Index: 3162638 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 3.1984. Min Range: -3.1984

Max Act: 3.0113. Min Act: -0.1700

Data Index: 8415215 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 3.1984. Min Range: -3.1984

Max Act: 3.0181. Min Act: -0.1700

Data Index: 1658611 (Open Web Text)

Max Activating Token Index: 513

Text #7

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9974. Min Act: -0.1700

Data Index: 5833027 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9912. Min Act: -0.1700

Data Index: 5128933 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9852. Min Act: -0.1700

Data Index: 8629226 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9896. Min Act: -0.1700

Data Index: 5949037 (Open Web Text)

Max Activating Token Index: 412

Text #11

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9827. Min Act: -0.1700

Data Index: 4859009 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9840. Min Act: -0.1700

Data Index: 6576975 (Open Web Text)

Max Activating Token Index: 729

Text #13

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9466. Min Act: -0.1700

Data Index: 2134176 (Open Web Text)

Max Activating Token Index: 170

Text #14

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9620. Min Act: -0.1700

Data Index: 3520741 (Open Web Text)

Max Activating Token Index: 203

Text #15

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9497. Min Act: -0.1700

Data Index: 3228902 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9610. Min Act: -0.1700

Data Index: 4481344 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9418. Min Act: -0.1700

Data Index: 1509977 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9086. Min Act: -0.1700

Data Index: 2249346 (Open Web Text)

Max Activating Token Index: 749

Text #19

Max Range: 3.1984. Min Range: -3.1984

Max Act: 2.9177. Min Act: -0.1700

Data Index: 2621951 (Open Web Text)

Max Activating Token Index: 647