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

Dataset: Open Web Text

Neuron 778 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: 1.5762. Min Range: -1.5762

Max Act: 1.5762. Min Act: -0.1700

Data Index: 8420326 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.5276. Min Act: -0.1700

Data Index: 6756533 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.5309. Min Act: -0.1700

Data Index: 4839855 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.5285. Min Act: -0.1700

Data Index: 4703988 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.5102. Min Act: -0.1700

Data Index: 104803 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4930. Min Act: -0.1700

Data Index: 3814157 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4912. Min Act: -0.1700

Data Index: 1477402 (Open Web Text)

Max Activating Token Index: 109

Text #7

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4871. Min Act: -0.1700

Data Index: 214210 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4773. Min Act: -0.1700

Data Index: 2931209 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4709. Min Act: -0.1700

Data Index: 1338348 (Open Web Text)

Max Activating Token Index: 332

Text #10

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4883. Min Act: -0.1700

Data Index: 3056916 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4767. Min Act: -0.1700

Data Index: 1895178 (Open Web Text)

Max Activating Token Index: 19

Text #12

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4745. Min Act: -0.1700

Data Index: 7225966 (Open Web Text)

Max Activating Token Index: 70

Text #13

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4720. Min Act: -0.1700

Data Index: 8388305 (Open Web Text)

Max Activating Token Index: 31

Text #14

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4757. Min Act: -0.1700

Data Index: 1191874 (Open Web Text)

Max Activating Token Index: 162

Text #15

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4673. Min Act: -0.1700

Data Index: 7906033 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4621. Min Act: -0.1700

Data Index: 6156104 (Open Web Text)

Max Activating Token Index: 612

Text #17

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4612. Min Act: -0.1700

Data Index: 6458378 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4543. Min Act: -0.1700

Data Index: 5544860 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 1.5762. Min Range: -1.5762

Max Act: 1.4577. Min Act: -0.1700

Data Index: 8152127 (Open Web Text)

Max Activating Token Index: 23