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

Dataset: Open Web Text

Neuron 2373 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: 3.2907. Min Range: -3.2907

Max Act: 3.2907. Min Act: -0.1700

Data Index: 8578826 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2738. Min Act: -0.1700

Data Index: 7983757 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2731. Min Act: -0.1700

Data Index: 7894953 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2705. Min Act: -0.1700

Data Index: 7297400 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2590. Min Act: -0.1700

Data Index: 5202003 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2367. Min Act: -0.1700

Data Index: 6401437 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2490. Min Act: -0.1700

Data Index: 590434 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2165. Min Act: -0.1700

Data Index: 3885088 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2120. Min Act: -0.1700

Data Index: 7987527 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2047. Min Act: -0.1700

Data Index: 7213964 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2048. Min Act: -0.1700

Data Index: 1101252 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2096. Min Act: -0.1700

Data Index: 1961274 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2050. Min Act: -0.1700

Data Index: 1891828 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2183. Min Act: -0.1700

Data Index: 6281114 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.2036. Min Act: -0.1700

Data Index: 2700602 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.1928. Min Act: -0.1700

Data Index: 3763729 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.1865. Min Act: -0.1700

Data Index: 181075 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.1916. Min Act: -0.1700

Data Index: 6865361 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.1960. Min Act: -0.1700

Data Index: 2215356 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.2907. Min Range: -3.2907

Max Act: 3.1833. Min Act: -0.1700

Data Index: 294980 (Open Web Text)

Max Activating Token Index: 6