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

Dataset: Open Web Text

Neuron 238 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: 3.1756. Min Range: -3.1756

Max Act: 3.1756. Min Act: -0.1700

Data Index: 4056998 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.1530. Min Act: -0.1700

Data Index: 346789 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.1335. Min Act: -0.1700

Data Index: 7979262 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.1222. Min Act: -0.1700

Data Index: 2056210 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.1227. Min Act: -0.1700

Data Index: 3422304 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.1174. Min Act: -0.1700

Data Index: 5438171 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.1080. Min Act: -0.1700

Data Index: 8675358 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0872. Min Act: -0.1700

Data Index: 6026207 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0913. Min Act: -0.1700

Data Index: 1003100 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0926. Min Act: -0.1700

Data Index: 5499790 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0888. Min Act: -0.1700

Data Index: 2048617 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0910. Min Act: -0.1700

Data Index: 7099049 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0926. Min Act: -0.1700

Data Index: 8659851 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0726. Min Act: -0.1700

Data Index: 8141810 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0760. Min Act: -0.1700

Data Index: 7854717 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0727. Min Act: -0.1700

Data Index: 8424768 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0851. Min Act: -0.1700

Data Index: 978301 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0736. Min Act: -0.1700

Data Index: 5779101 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0694. Min Act: -0.1700

Data Index: 5959507 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.1756. Min Range: -3.1756

Max Act: 3.0801. Min Act: -0.1700

Data Index: 8572161 (Open Web Text)

Max Activating Token Index: 633