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

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

Neuron 1809 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.8083. Min Act: -0.0000

Data Index: 997908 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.8718. Min Act: -0.0000

Data Index: 283085 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1251228 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7364. Min Act: -0.0000

Data Index: 99257 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7413. Min Act: -0.0000

Data Index: 797746 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7040. Min Act: -0.0000

Data Index: 615125 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7370. Min Act: -0.0000

Data Index: 897085 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6962. Min Act: -0.0000

Data Index: 282803 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1055784 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6835. Min Act: -0.0000

Data Index: 803355 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6737. Min Act: -0.0000

Data Index: 600298 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1337869 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6675. Min Act: -0.0000

Data Index: 940715 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6796. Min Act: -0.0000

Data Index: 6198 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6142. Min Act: -0.0000

Data Index: 918128 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6687. Min Act: -0.0000

Data Index: 716989 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.7173. Min Act: -0.0000

Data Index: 307024 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6515. Min Act: -0.0000

Data Index: 589952 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6650. Min Act: -0.0000

Data Index: 958872 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.8718. Min Range: -0.8718

Max Act: 0.6414. Min Act: -0.0000

Data Index: 473083 (C4 (Web Text))

Max Activating Token Index: 733