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

Dataset: Open Web Text

Neuron 60 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: 3.0055. Min Range: -3.0055

Max Act: 3.0055. Min Act: -0.1700

Data Index: 8443684 (Open Web Text)

Max Activating Token Index: 245

Text #1

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9747. Min Act: -0.1700

Data Index: 1783296 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9390. Min Act: -0.1700

Data Index: 6331958 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9250. Min Act: -0.1700

Data Index: 2372351 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9164. Min Act: -0.1700

Data Index: 8727011 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9074. Min Act: -0.1700

Data Index: 4194955 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9132. Min Act: -0.1700

Data Index: 7626158 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9009. Min Act: -0.1700

Data Index: 8577498 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9065. Min Act: -0.1700

Data Index: 3175499 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8934. Min Act: -0.1700

Data Index: 2010794 (Open Web Text)

Max Activating Token Index: 21

Text #10

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8839. Min Act: -0.1700

Data Index: 335916 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8908. Min Act: -0.1700

Data Index: 3135297 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8933. Min Act: -0.1700

Data Index: 5679865 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9094. Min Act: -0.1700

Data Index: 1588992 (Open Web Text)

Max Activating Token Index: 943

Text #14

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8983. Min Act: -0.1700

Data Index: 3767058 (Open Web Text)

Max Activating Token Index: 53

Text #15

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.9020. Min Act: -0.1700

Data Index: 3683006 (Open Web Text)

Max Activating Token Index: 709

Text #16

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8714. Min Act: -0.1700

Data Index: 516757 (Open Web Text)

Max Activating Token Index: 797

Text #17

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8816. Min Act: -0.1700

Data Index: 5608821 (Open Web Text)

Max Activating Token Index: 850

Text #18

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8799. Min Act: -0.1700

Data Index: 4696552 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 3.0055. Min Range: -3.0055

Max Act: 2.8773. Min Act: -0.1700

Data Index: 2435406 (Open Web Text)

Max Activating Token Index: 7