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

Dataset: Open Web Text

Neuron 1637 in Layer 2

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: 2.3897. Min Range: -2.3897

Max Act: 2.3897. Min Act: -0.1700

Data Index: 8446454 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1672. Min Act: -0.1700

Data Index: 2871506 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1831. Min Act: -0.1700

Data Index: 4708819 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1706. Min Act: -0.1700

Data Index: 4260795 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1788. Min Act: -0.1700

Data Index: 4507907 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1605. Min Act: -0.1700

Data Index: 7630287 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1612. Min Act: -0.1700

Data Index: 18989 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1468. Min Act: -0.1700

Data Index: 7431962 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1450. Min Act: -0.1700

Data Index: 1166727 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1531. Min Act: -0.1700

Data Index: 759194 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.0977. Min Act: -0.1700

Data Index: 7418554 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1014. Min Act: -0.1700

Data Index: 7679120 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1139. Min Act: -0.1700

Data Index: 4105748 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.1028. Min Act: -0.1700

Data Index: 2519667 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.0880. Min Act: -0.1700

Data Index: 5746466 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.0599. Min Act: -0.1700

Data Index: 7787651 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.0758. Min Act: -0.1700

Data Index: 3091776 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.0711. Min Act: -0.1700

Data Index: 4993670 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.0681. Min Act: -0.1700

Data Index: 7141965 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.3897. Min Range: -2.3897

Max Act: 2.0772. Min Act: -0.1700

Data Index: 2580675 (Open Web Text)

Max Activating Token Index: 1023