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

Dataset: Open Web Text

Neuron 3018 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: 0.7531. Min Range: -0.7531

Max Act: 0.7531. Min Act: -0.1700

Data Index: 4543223 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.7188. Min Act: -0.1700

Data Index: 7746718 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.7121. Min Act: -0.1700

Data Index: 1513827 (Open Web Text)

Max Activating Token Index: 296

Text #3

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6959. Min Act: -0.1700

Data Index: 8823211 (Open Web Text)

Max Activating Token Index: 875

Text #4

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6956. Min Act: -0.1700

Data Index: 6345361 (Open Web Text)

Max Activating Token Index: 883

Text #5

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6934. Min Act: -0.1700

Data Index: 928966 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6914. Min Act: -0.1700

Data Index: 1704615 (Open Web Text)

Max Activating Token Index: 877

Text #7

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6927. Min Act: -0.1700

Data Index: 3741708 (Open Web Text)

Max Activating Token Index: 881

Text #8

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6763. Min Act: -0.1700

Data Index: 6671911 (Open Web Text)

Max Activating Token Index: 862

Text #9

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6656. Min Act: -0.1700

Data Index: 4021753 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6825. Min Act: -0.1700

Data Index: 6184777 (Open Web Text)

Max Activating Token Index: 872

Text #11

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6781. Min Act: -0.1700

Data Index: 5304011 (Open Web Text)

Max Activating Token Index: 306

Text #12

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6654. Min Act: -0.1700

Data Index: 6850377 (Open Web Text)

Max Activating Token Index: 882

Text #13

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6723. Min Act: -0.1700

Data Index: 3665880 (Open Web Text)

Max Activating Token Index: 868

Text #14

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6798. Min Act: -0.1700

Data Index: 7957733 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6688. Min Act: -0.1700

Data Index: 2332620 (Open Web Text)

Max Activating Token Index: 875

Text #16

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6646. Min Act: -0.1700

Data Index: 8684293 (Open Web Text)

Max Activating Token Index: 867

Text #17

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6668. Min Act: -0.1700

Data Index: 5550820 (Open Web Text)

Max Activating Token Index: 884

Text #18

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6714. Min Act: -0.1700

Data Index: 5200766 (Open Web Text)

Max Activating Token Index: 881

Text #19

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6703. Min Act: -0.1700

Data Index: 1290054 (Open Web Text)

Max Activating Token Index: 874