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

Dataset: Open Web Text

Neuron 2302 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: 4.4312. Min Range: -4.4312

Max Act: 4.4312. Min Act: -0.1700

Data Index: 508876 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.3938. Min Act: -0.1700

Data Index: 7065006 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.3048. Min Act: -0.1700

Data Index: 7061761 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2924. Min Act: -0.1700

Data Index: 2434827 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2792. Min Act: -0.1700

Data Index: 3152508 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2588. Min Act: -0.1700

Data Index: 4343360 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2606. Min Act: -0.1700

Data Index: 5066615 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2407. Min Act: -0.1700

Data Index: 4863766 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2181. Min Act: -0.1700

Data Index: 1630060 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2162. Min Act: -0.1700

Data Index: 4386368 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.1911. Min Act: -0.1700

Data Index: 4831918 (Open Web Text)

Max Activating Token Index: 960

Text #11

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2075. Min Act: -0.1700

Data Index: 3945466 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.1959. Min Act: -0.1700

Data Index: 3198707 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.1960. Min Act: -0.1700

Data Index: 680620 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.1945. Min Act: -0.1700

Data Index: 3179646 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.1858. Min Act: -0.1700

Data Index: 6871199 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.1964. Min Act: -0.1700

Data Index: 3465291 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.2077. Min Act: -0.1700

Data Index: 4235713 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.1992. Min Act: -0.1700

Data Index: 4047939 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.4312. Min Range: -4.4312

Max Act: 4.1657. Min Act: -0.1700

Data Index: 5800734 (Open Web Text)

Max Activating Token Index: 4