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

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

Neuron 4031 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6801. Min Act: -0.0002

Data Index: 954076 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6946. Min Act: -0.0002

Data Index: 1046358 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6270. Min Act: -0.0002

Data Index: 265005 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6424. Min Act: -0.0003

Data Index: 117912 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6626. Min Act: -0.0003

Data Index: 94040 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6107. Min Act: -0.0002

Data Index: 436530 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6288. Min Act: -0.0003

Data Index: 562412 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6142. Min Act: -0.0003

Data Index: 38057 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6103. Min Act: -0.0003

Data Index: 278171 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6045. Min Act: -0.0002

Data Index: 69454 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6223. Min Act: -0.0002

Data Index: 23410 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.5794. Min Act: -0.0003

Data Index: 685061 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.5918. Min Act: -0.0002

Data Index: 1285830 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.6000. Min Act: -0.0003

Data Index: 546350 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.5851. Min Act: -0.0003

Data Index: 708660 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.5796. Min Act: -0.0003

Data Index: 559875 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.5992. Min Act: -0.0003

Data Index: 906566 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.5979. Min Act: -0.0003

Data Index: 1353013 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.5888. Min Act: -0.0003

Data Index: 1141831 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.6946. Min Range: -0.6946

Max Act: 0.5564. Min Act: -0.0003

Data Index: 399747 (C4 (Web Text))

Max Activating Token Index: 406