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

Dataset: Open Web Text

Neuron 1101 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: 2.8607. Min Range: -2.8607

Max Act: 2.8607. Min Act: -0.1700

Data Index: 2465373 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.8452. Min Act: -0.1700

Data Index: 612741 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.8309. Min Act: -0.1700

Data Index: 231437 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.8298. Min Act: -0.1700

Data Index: 4758435 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.8142. Min Act: -0.1700

Data Index: 883806 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.8145. Min Act: -0.1700

Data Index: 4490935 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7858. Min Act: -0.1700

Data Index: 7453335 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7962. Min Act: -0.1700

Data Index: 2303063 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7932. Min Act: -0.1700

Data Index: 6415968 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.8007. Min Act: -0.1700

Data Index: 4104046 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7941. Min Act: -0.1700

Data Index: 8753831 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7923. Min Act: -0.1700

Data Index: 3737694 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7804. Min Act: -0.1700

Data Index: 7183389 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7800. Min Act: -0.1700

Data Index: 2129169 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7763. Min Act: -0.1700

Data Index: 4625978 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7724. Min Act: -0.1700

Data Index: 6796914 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7817. Min Act: -0.1700

Data Index: 8513372 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7759. Min Act: -0.1700

Data Index: 3821685 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7778. Min Act: -0.1700

Data Index: 674137 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.8607. Min Range: -2.8607

Max Act: 2.7682. Min Act: -0.1700

Data Index: 3569585 (Open Web Text)

Max Activating Token Index: 3