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

Dataset: Open Web Text

Neuron 809 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: 4.9310. Min Range: -4.9310

Max Act: 4.9310. Min Act: -0.1700

Data Index: 8307376 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.9011. Min Act: -0.1700

Data Index: 7036623 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.7920. Min Act: -0.1700

Data Index: 6071292 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.8038. Min Act: -0.1700

Data Index: 1196694 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.7815. Min Act: -0.1700

Data Index: 7599525 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.7567. Min Act: -0.1700

Data Index: 7545550 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6730. Min Act: -0.1700

Data Index: 8383744 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6333. Min Act: -0.1700

Data Index: 5205151 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6333. Min Act: -0.1700

Data Index: 5687653 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6333. Min Act: -0.1700

Data Index: 3292484 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6353. Min Act: -0.1700

Data Index: 90649 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6567. Min Act: -0.1700

Data Index: 6520839 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6333. Min Act: -0.1700

Data Index: 8359360 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6081. Min Act: -0.1700

Data Index: 6904625 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.6191. Min Act: -0.1700

Data Index: 3314477 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.4907. Min Act: -0.1700

Data Index: 8373905 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.4970. Min Act: -0.1700

Data Index: 1002518 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.4640. Min Act: -0.1700

Data Index: 4687904 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.4481. Min Act: -0.1700

Data Index: 4661426 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 4.9310. Min Range: -4.9310

Max Act: 4.4588. Min Act: -0.1700

Data Index: 2824960 (Open Web Text)

Max Activating Token Index: 411