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

Dataset: Open Web Text

Neuron 2407 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: 3.2762. Min Range: -3.2762

Max Act: 3.2762. Min Act: -0.1700

Data Index: 5591770 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2471. Min Act: -0.1700

Data Index: 5788895 (Open Web Text)

Max Activating Token Index: 839

Text #2

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2539. Min Act: -0.1700

Data Index: 2992871 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2205. Min Act: -0.1700

Data Index: 3119108 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2255. Min Act: -0.1700

Data Index: 3551675 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2166. Min Act: -0.1700

Data Index: 5286985 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2106. Min Act: -0.1700

Data Index: 3931623 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2090. Min Act: -0.1700

Data Index: 761915 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2158. Min Act: -0.1700

Data Index: 934314 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2135. Min Act: -0.1700

Data Index: 3306734 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.2054. Min Act: -0.1700

Data Index: 7541334 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1840. Min Act: -0.1700

Data Index: 4243420 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1913. Min Act: -0.1700

Data Index: 4159279 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1852. Min Act: -0.1700

Data Index: 4147271 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1819. Min Act: -0.1700

Data Index: 3965452 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1925. Min Act: -0.1700

Data Index: 3938234 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1793. Min Act: -0.1700

Data Index: 3755355 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1813. Min Act: -0.1700

Data Index: 2500586 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1877. Min Act: -0.1700

Data Index: 2338056 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.2762. Min Range: -3.2762

Max Act: 3.1881. Min Act: -0.1700

Data Index: 3399952 (Open Web Text)

Max Activating Token Index: 8