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

Dataset: Open Web Text

Neuron 957 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: 2.8740. Min Range: -2.8740

Max Act: 2.8740. Min Act: -0.1700

Data Index: 8180903 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.8591. Min Act: -0.1700

Data Index: 2093019 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.8261. Min Act: -0.1700

Data Index: 110460 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.8089. Min Act: -0.1700

Data Index: 6865892 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.8211. Min Act: -0.1700

Data Index: 7275438 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.8169. Min Act: -0.1700

Data Index: 8803669 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7940. Min Act: -0.1700

Data Index: 3824089 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7804. Min Act: -0.1700

Data Index: 6567645 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7838. Min Act: -0.1700

Data Index: 4676759 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7888. Min Act: -0.1700

Data Index: 6275839 (Open Web Text)

Max Activating Token Index: 62

Text #10

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7827. Min Act: -0.1700

Data Index: 5476422 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7848. Min Act: -0.1700

Data Index: 2277713 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7791. Min Act: -0.1700

Data Index: 3105329 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7791. Min Act: -0.1700

Data Index: 5391149 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7998. Min Act: -0.1700

Data Index: 1650801 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7802. Min Act: -0.1700

Data Index: 7417919 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7687. Min Act: -0.1700

Data Index: 2253231 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7699. Min Act: -0.1700

Data Index: 3636996 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7706. Min Act: -0.1700

Data Index: 3669538 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.8740. Min Range: -2.8740

Max Act: 2.7688. Min Act: -0.1700

Data Index: 2894070 (Open Web Text)

Max Activating Token Index: 3