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

Dataset: Open Web Text

Neuron 2837 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: 5.6772. Min Range: -5.6772

Max Act: 5.6772. Min Act: -0.1700

Data Index: 4191138 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6530. Min Act: -0.1700

Data Index: 6213624 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6449. Min Act: -0.1700

Data Index: 80099 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6666. Min Act: -0.1700

Data Index: 941781 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6565. Min Act: -0.1700

Data Index: 8349062 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6185. Min Act: -0.1700

Data Index: 8016921 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6098. Min Act: -0.1700

Data Index: 6686274 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6067. Min Act: -0.1700

Data Index: 805951 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5910. Min Act: -0.1700

Data Index: 2810441 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6087. Min Act: -0.1700

Data Index: 4800374 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5971. Min Act: -0.1700

Data Index: 3776201 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.6029. Min Act: -0.1700

Data Index: 3753171 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5831. Min Act: -0.1700

Data Index: 3483497 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5745. Min Act: -0.1700

Data Index: 503671 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5924. Min Act: -0.1700

Data Index: 8139613 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5729. Min Act: -0.1700

Data Index: 1694898 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5786. Min Act: -0.1700

Data Index: 4770015 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5610. Min Act: -0.1700

Data Index: 5014468 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5499. Min Act: -0.1700

Data Index: 5571757 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.6772. Min Range: -5.6772

Max Act: 5.5762. Min Act: -0.1700

Data Index: 7143893 (Open Web Text)

Max Activating Token Index: 3