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

Dataset: Open Web Text

Neuron 1851 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: 2.7865. Min Range: -2.7865

Max Act: 2.7798. Min Act: -0.1700

Data Index: 1073405 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7865. Min Act: -0.1700

Data Index: 6117347 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7617. Min Act: -0.1700

Data Index: 3998166 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7294. Min Act: -0.1700

Data Index: 5191982 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7110. Min Act: -0.1700

Data Index: 5538940 (Open Web Text)

Max Activating Token Index: 962

Text #5

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7198. Min Act: -0.1700

Data Index: 2496545 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7265. Min Act: -0.1700

Data Index: 7684075 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6942. Min Act: -0.1700

Data Index: 2234929 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7061. Min Act: -0.1700

Data Index: 3585560 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7071. Min Act: -0.1700

Data Index: 8013602 (Open Web Text)

Max Activating Token Index: 646

Text #10

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7111. Min Act: -0.1700

Data Index: 6390164 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6845. Min Act: -0.1700

Data Index: 4187935 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6845. Min Act: -0.1700

Data Index: 6121186 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6761. Min Act: -0.1700

Data Index: 5804376 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6911. Min Act: -0.1700

Data Index: 5564414 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6880. Min Act: -0.1700

Data Index: 1873681 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6831. Min Act: -0.1700

Data Index: 5729094 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6908. Min Act: -0.1700

Data Index: 8148000 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6730. Min Act: -0.1700

Data Index: 5631351 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6884. Min Act: -0.1700

Data Index: 1288930 (Open Web Text)

Max Activating Token Index: 5