Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4281 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1113. Min Act: -0.0001

Data Index: 24415 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1152173 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1047. Min Act: -0.0001

Data Index: 861985 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1189977 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1005. Min Act: -0.0001

Data Index: 261981 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0886. Min Act: -0.0001

Data Index: 781274 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1284988 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0934. Min Act: -0.0001

Data Index: 763787 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0870. Min Act: -0.0001

Data Index: 629235 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0904. Min Act: -0.0001

Data Index: 156975 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1016. Min Act: -0.0001

Data Index: 488656 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0888. Min Act: -0.0001

Data Index: 153571 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1026500 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0869. Min Act: -0.0001

Data Index: 798978 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0848. Min Act: -0.0001

Data Index: 54788 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0823. Min Act: -0.0001

Data Index: 214435 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0885. Min Act: -0.0001

Data Index: 597726 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1102736 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0853. Min Act: -0.0001

Data Index: 466506 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0865. Min Act: -0.0001

Data Index: 399092 (C4 (Web Text))

Max Activating Token Index: 763