Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2795 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.6029. Min Range: -6.6029

Max Act: 6.6029. Min Act: -0.0000

Data Index: 1397422 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 6.6029. Min Range: -6.6029

Max Act: 6.2053. Min Act: -0.0000

Data Index: 1508057 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 6.6029. Min Range: -6.6029

Max Act: 6.0818. Min Act: -0.0000

Data Index: 492603 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.6634. Min Act: -0.0000

Data Index: 1561072 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.9453. Min Act: -0.0000

Data Index: 1417435 (Python Code)

Max Activating Token Index: 891

Text #5

Max Range: 6.6029. Min Range: -6.6029

Max Act: 6.2640. Min Act: -0.0000

Data Index: 805202 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 6.6029. Min Range: -6.6029

Max Act: 6.1975. Min Act: -0.0000

Data Index: 1620916 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.6522. Min Act: -0.0000

Data Index: 1540305 (Python Code)

Max Activating Token Index: 720

Text #8

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.7892. Min Act: -0.0000

Data Index: 1471755 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 6.6029. Min Range: -6.6029

Max Act: 6.0781. Min Act: -0.0000

Data Index: 1404826 (Python Code)

Max Activating Token Index: 975

Text #10

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.8757. Min Act: -0.0000

Data Index: 1431717 (Python Code)

Max Activating Token Index: 688

Text #11

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.6939. Min Act: -0.0000

Data Index: 1618798 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 6.6029. Min Range: -6.6029

Max Act: 6.0585. Min Act: -0.0000

Data Index: 1648936 (Python Code)

Max Activating Token Index: 979

Text #13

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.9367. Min Act: -0.0000

Data Index: 1423449 (Python Code)

Max Activating Token Index: 836

Text #14

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.7926. Min Act: -0.0000

Data Index: 1593267 (Python Code)

Max Activating Token Index: 946

Text #15

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.8050. Min Act: -0.0000

Data Index: 1616992 (Python Code)

Max Activating Token Index: 873

Text #16

Max Range: 6.6029. Min Range: -6.6029

Max Act: 6.0945. Min Act: -0.0000

Data Index: 1189107 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.5653. Min Act: -0.0000

Data Index: 949041 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.5574. Min Act: -0.0000

Data Index: 1389049 (Python Code)

Max Activating Token Index: 995

Text #19

Max Range: 6.6029. Min Range: -6.6029

Max Act: 5.6828. Min Act: -0.0000

Data Index: 1586845 (Python Code)

Max Activating Token Index: 894