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

Dataset: Open Web Text

Neuron 1998 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: 4.0590. Min Range: -4.0590

Max Act: 4.0590. Min Act: -0.1700

Data Index: 1562984 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.0590. Min Range: -4.0590

Max Act: 4.0581. Min Act: -0.1700

Data Index: 6222428 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.0590. Min Range: -4.0590

Max Act: 4.0106. Min Act: -0.1700

Data Index: 2348620 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.0590. Min Range: -4.0590

Max Act: 4.0139. Min Act: -0.1700

Data Index: 6986556 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9402. Min Act: -0.1700

Data Index: 8472058 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9083. Min Act: -0.1700

Data Index: 6073464 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9015. Min Act: -0.1700

Data Index: 3574900 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9231. Min Act: -0.1700

Data Index: 2162947 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9083. Min Act: -0.1700

Data Index: 8406157 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9099. Min Act: -0.1700

Data Index: 3135744 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9197. Min Act: -0.1700

Data Index: 2631282 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9103. Min Act: -0.1700

Data Index: 1908273 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9171. Min Act: -0.1700

Data Index: 962830 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.9054. Min Act: -0.1700

Data Index: 6077401 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.8779. Min Act: -0.1700

Data Index: 7212830 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.8815. Min Act: -0.1700

Data Index: 2952026 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.8915. Min Act: -0.1700

Data Index: 42226 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.8786. Min Act: -0.1700

Data Index: 1027883 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.8691. Min Act: -0.1700

Data Index: 833020 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.0590. Min Range: -4.0590

Max Act: 3.8782. Min Act: -0.1700

Data Index: 3804590 (Open Web Text)

Max Activating Token Index: 6