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

Dataset: Open Web Text

Neuron 1404 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: 3.7078. Min Range: -3.7078

Max Act: 3.7078. Min Act: -0.1700

Data Index: 1453281 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.6447. Min Act: -0.1700

Data Index: 5425523 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.6447. Min Act: -0.1700

Data Index: 8474427 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5641. Min Act: -0.1700

Data Index: 6497527 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5674. Min Act: -0.1700

Data Index: 7031237 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5448. Min Act: -0.1700

Data Index: 6466685 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5495. Min Act: -0.1700

Data Index: 3495990 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5452. Min Act: -0.1700

Data Index: 3015510 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5301. Min Act: -0.1700

Data Index: 5996959 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5452. Min Act: -0.1700

Data Index: 2339834 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5452. Min Act: -0.1700

Data Index: 5123896 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5452. Min Act: -0.1700

Data Index: 1006789 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5495. Min Act: -0.1700

Data Index: 6625690 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5495. Min Act: -0.1700

Data Index: 994555 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5364. Min Act: -0.1700

Data Index: 132016 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5084. Min Act: -0.1700

Data Index: 2811735 (Open Web Text)

Max Activating Token Index: 24

Text #16

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5215. Min Act: -0.1700

Data Index: 5437782 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5035. Min Act: -0.1700

Data Index: 1420374 (Open Web Text)

Max Activating Token Index: 822

Text #18

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5168. Min Act: -0.1700

Data Index: 5641269 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5123. Min Act: -0.1700

Data Index: 1516119 (Open Web Text)

Max Activating Token Index: 9