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

Dataset: Open Web Text

Neuron 2733 in Layer 0

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: 5.9861. Min Range: -5.9861

Max Act: 5.9861. Min Act: -0.1700

Data Index: 480038 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.9861. Min Act: -0.1700

Data Index: 7653113 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.9589. Min Act: -0.1700

Data Index: 7267132 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.9719. Min Act: -0.1700

Data Index: 6992195 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8913. Min Act: -0.1700

Data Index: 6185711 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.9158. Min Act: -0.1700

Data Index: 2980120 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.9154. Min Act: -0.1700

Data Index: 539501 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8625. Min Act: -0.1700

Data Index: 1912816 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8618. Min Act: -0.1700

Data Index: 6508803 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8949. Min Act: -0.1700

Data Index: 6952346 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8655. Min Act: -0.1700

Data Index: 3147831 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8625. Min Act: -0.1700

Data Index: 5009727 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8952. Min Act: -0.1700

Data Index: 3613972 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.9007. Min Act: -0.1700

Data Index: 4365973 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8946. Min Act: -0.1700

Data Index: 8359911 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8625. Min Act: -0.1700

Data Index: 1700368 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8697. Min Act: -0.1700

Data Index: 8759125 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8711. Min Act: -0.1700

Data Index: 4014369 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8655. Min Act: -0.1700

Data Index: 4276830 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.9861. Min Range: -5.9861

Max Act: 5.8619. Min Act: -0.1700

Data Index: 4075248 (Open Web Text)

Max Activating Token Index: 4