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

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

Neuron 2156 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.8704. Min Act: -0.0000

Data Index: 1525297 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.3594. Min Act: -0.0000

Data Index: 1395426 (Python Code)

Max Activating Token Index: 820

Text #2

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.5320. Min Act: -0.0000

Data Index: 1632749 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.5320. Min Act: -0.0000

Data Index: 1581238 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.5320. Min Act: -0.0000

Data Index: 1430008 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.3632. Min Act: -0.0000

Data Index: 1509309 (Python Code)

Max Activating Token Index: 829

Text #6

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.1734. Min Act: -0.0000

Data Index: 1647610 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.4667. Min Act: -0.0000

Data Index: 1368215 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.3314. Min Act: -0.0000

Data Index: 1635115 (Python Code)

Max Activating Token Index: 733

Text #9

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.2730. Min Act: -0.0000

Data Index: 1396722 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.2673. Min Act: -0.0000

Data Index: 1441625 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.2375. Min Act: -0.0000

Data Index: 1437431 (Python Code)

Max Activating Token Index: 885

Text #12

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.7953. Min Act: -0.0000

Data Index: 1459146 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.3949. Min Act: -0.0000

Data Index: 1515539 (Python Code)

Max Activating Token Index: 993

Text #14

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.0718. Min Act: -0.0000

Data Index: 1634048 (Python Code)

Max Activating Token Index: 954

Text #15

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.1374. Min Act: -0.0000

Data Index: 1499190 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.4993. Min Act: -0.0000

Data Index: 1375001 (Python Code)

Max Activating Token Index: 944

Text #17

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.1959. Min Act: -0.0000

Data Index: 1615134 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.1940. Min Act: -0.0000

Data Index: 1412649 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 4.8704. Min Range: -4.8704

Max Act: 4.1940. Min Act: -0.0000

Data Index: 1430959 (Python Code)

Max Activating Token Index: 9