Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1964 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1312328 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0963. Min Act: -0.0001

Data Index: 167723 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1018702 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1175468 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0884. Min Act: -0.0001

Data Index: 791505 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0878. Min Act: -0.0001

Data Index: 928312 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0887. Min Act: -0.0001

Data Index: 187385 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0908. Min Act: -0.0001

Data Index: 338708 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0909. Min Act: -0.0001

Data Index: 24219 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1598907 (Python Code)

Max Activating Token Index: 1003

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1584915 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1635657 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0913. Min Act: -0.0001

Data Index: 406702 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0885. Min Act: -0.0001

Data Index: 780161 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0831. Min Act: -0.0001

Data Index: 999834 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0868. Min Act: -0.0001

Data Index: 238617 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1312323 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1324384 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0915. Min Act: -0.0001

Data Index: 236591 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1583399 (Python Code)

Max Activating Token Index: 88