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

Dataset: Open Web Text

Neuron 2983 in Layer 3

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: 3.6926. Min Range: -3.6926

Max Act: 3.6926. Min Act: -0.1700

Data Index: 2721910 (Open Web Text)

Max Activating Token Index: 974

Text #1

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.5432. Min Act: -0.1700

Data Index: 452839 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.5491. Min Act: -0.1700

Data Index: 6024566 (Open Web Text)

Max Activating Token Index: 39

Text #3

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.5520. Min Act: -0.1700

Data Index: 7296057 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.5228. Min Act: -0.1700

Data Index: 7659058 (Open Web Text)

Max Activating Token Index: 166

Text #5

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.5183. Min Act: -0.1700

Data Index: 2824796 (Open Web Text)

Max Activating Token Index: 274

Text #6

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.5335. Min Act: -0.1700

Data Index: 5440086 (Open Web Text)

Max Activating Token Index: 221

Text #7

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.5299. Min Act: -0.1700

Data Index: 5829702 (Open Web Text)

Max Activating Token Index: 569

Text #8

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.5000. Min Act: -0.1700

Data Index: 7283293 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4990. Min Act: -0.1700

Data Index: 7165941 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4990. Min Act: -0.1700

Data Index: 1490756 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4838. Min Act: -0.1700

Data Index: 8234579 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4795. Min Act: -0.1700

Data Index: 2489980 (Open Web Text)

Max Activating Token Index: 886

Text #13

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4903. Min Act: -0.1700

Data Index: 5757722 (Open Web Text)

Max Activating Token Index: 910

Text #14

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4695. Min Act: -0.1700

Data Index: 5278745 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4823. Min Act: -0.1700

Data Index: 1554224 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4576. Min Act: -0.1700

Data Index: 2058655 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4475. Min Act: -0.1700

Data Index: 6442701 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4741. Min Act: -0.1700

Data Index: 3795130 (Open Web Text)

Max Activating Token Index: 841

Text #19

Max Range: 3.6926. Min Range: -3.6926

Max Act: 3.4804. Min Act: -0.1700

Data Index: 2497589 (Open Web Text)

Max Activating Token Index: 182