Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2975 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.1995. Min Act: -0.0003

Data Index: 1485316 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.1138. Min Act: -0.0003

Data Index: 1646108 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.1037. Min Act: -0.0003

Data Index: 1385198 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0948. Min Act: -0.0003

Data Index: 1502571 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0960. Min Act: -0.0003

Data Index: 1508833 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0918. Min Act: -0.0003

Data Index: 1628972 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0987. Min Act: -0.0003

Data Index: 1544095 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.1005. Min Act: -0.0003

Data Index: 1592036 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0813. Min Act: -0.0003

Data Index: 1488363 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0753. Min Act: -0.0003

Data Index: 428102 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1511989 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1388971 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1573535 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1003252 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1435332 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1447119 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1460412 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1311780 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1453838 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1995. Min Range: -0.1995

Max Act: 0.0622. Min Act: -0.0003

Data Index: 646753 (C4 (Web Text))

Max Activating Token Index: 1023