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

Dataset: Open Web Text

Neuron 1854 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: 4.5875. Min Range: -4.5875

Max Act: 4.5672. Min Act: -0.1700

Data Index: 7224338 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.5875. Min Act: -0.1700

Data Index: 4052815 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.5540. Min Act: -0.1700

Data Index: 3777577 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.5687. Min Act: -0.1700

Data Index: 5554152 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.5254. Min Act: -0.1700

Data Index: 2437307 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.5118. Min Act: -0.1700

Data Index: 5699375 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.5153. Min Act: -0.1700

Data Index: 125548 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4988. Min Act: -0.1700

Data Index: 7493197 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.5167. Min Act: -0.1700

Data Index: 2226454 (Open Web Text)

Max Activating Token Index: 779

Text #9

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4778. Min Act: -0.1700

Data Index: 8087438 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.5066. Min Act: -0.1700

Data Index: 5274198 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4829. Min Act: -0.1700

Data Index: 4342471 (Open Web Text)

Max Activating Token Index: 551

Text #12

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4902. Min Act: -0.1700

Data Index: 4328915 (Open Web Text)

Max Activating Token Index: 1006

Text #13

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4998. Min Act: -0.1700

Data Index: 3794615 (Open Web Text)

Max Activating Token Index: 988

Text #14

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4744. Min Act: -0.1700

Data Index: 2237165 (Open Web Text)

Max Activating Token Index: 796

Text #15

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4717. Min Act: -0.1700

Data Index: 2185136 (Open Web Text)

Max Activating Token Index: 938

Text #16

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4830. Min Act: -0.1700

Data Index: 7477804 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4850. Min Act: -0.1700

Data Index: 3737929 (Open Web Text)

Max Activating Token Index: 947

Text #18

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4845. Min Act: -0.1700

Data Index: 6317397 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 4.5875. Min Range: -4.5875

Max Act: 4.4599. Min Act: -0.1700

Data Index: 6271895 (Open Web Text)

Max Activating Token Index: 865