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

Dataset: Open Web Text

Neuron 2287 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: 5.2323. Min Range: -5.2323

Max Act: 5.2274. Min Act: -0.1700

Data Index: 7298969 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.2323. Min Act: -0.1700

Data Index: 4838294 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.2198. Min Act: -0.1700

Data Index: 4877741 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.2323. Min Act: -0.1700

Data Index: 6480855 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1782. Min Act: -0.1700

Data Index: 7558890 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1733. Min Act: -0.1700

Data Index: 5175984 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1422. Min Act: -0.1700

Data Index: 7879085 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1603. Min Act: -0.1700

Data Index: 3782159 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1274. Min Act: -0.1700

Data Index: 1978559 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1277. Min Act: -0.1700

Data Index: 8030303 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1141. Min Act: -0.1700

Data Index: 3416466 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1494. Min Act: -0.1700

Data Index: 7573412 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1179. Min Act: -0.1700

Data Index: 4265182 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1332. Min Act: -0.1700

Data Index: 8549620 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1427. Min Act: -0.1700

Data Index: 4494747 (Open Web Text)

Max Activating Token Index: 936

Text #15

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.1067. Min Act: -0.1700

Data Index: 1575848 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.0926. Min Act: -0.1700

Data Index: 2175930 (Open Web Text)

Max Activating Token Index: 912

Text #17

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.0834. Min Act: -0.1700

Data Index: 5978196 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.0663. Min Act: -0.1700

Data Index: 1312616 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 5.2323. Min Range: -5.2323

Max Act: 5.0851. Min Act: -0.1700

Data Index: 5799186 (Open Web Text)

Max Activating Token Index: 8