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

Dataset: Open Web Text

Neuron 1144 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: 2.7130. Min Range: -2.7130

Max Act: 2.7128. Min Act: -0.1700

Data Index: 8513608 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6934. Min Act: -0.1700

Data Index: 3519586 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.7130. Min Act: -0.1700

Data Index: 3701194 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6877. Min Act: -0.1700

Data Index: 6856803 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6856. Min Act: -0.1700

Data Index: 5431972 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6760. Min Act: -0.1700

Data Index: 2534549 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6783. Min Act: -0.1700

Data Index: 3117679 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6932. Min Act: -0.1700

Data Index: 3670135 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6791. Min Act: -0.1700

Data Index: 4119982 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6925. Min Act: -0.1700

Data Index: 3241969 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6757. Min Act: -0.1700

Data Index: 1487343 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6647. Min Act: -0.1700

Data Index: 4217350 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6718. Min Act: -0.1700

Data Index: 3198396 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6651. Min Act: -0.1700

Data Index: 2421187 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6703. Min Act: -0.1700

Data Index: 3847898 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6673. Min Act: -0.1700

Data Index: 2231960 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6613. Min Act: -0.1700

Data Index: 8513611 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6545. Min Act: -0.1700

Data Index: 7333117 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6522. Min Act: -0.1700

Data Index: 1518280 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 2.7130. Min Range: -2.7130

Max Act: 2.6525. Min Act: -0.1700

Data Index: 1852351 (Open Web Text)

Max Activating Token Index: 16