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

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

Neuron 1375 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7985. Min Act: -0.0000

Data Index: 959321 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5567. Min Act: -0.0000

Data Index: 55904 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1342139 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6661. Min Act: -0.0000

Data Index: 407038 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7380. Min Act: -0.0000

Data Index: 633190 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1087659 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1114006 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7377. Min Act: -0.0000

Data Index: 287536 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1267634 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6716. Min Act: -0.0000

Data Index: 35714 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7988. Min Act: -0.0000

Data Index: 584983 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7013. Min Act: -0.0000

Data Index: 559295 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6832. Min Act: -0.0000

Data Index: 378346 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6944. Min Act: -0.0000

Data Index: 261014 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1612619 (Python Code)

Max Activating Token Index: 991

Text #15

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6687. Min Act: -0.0000

Data Index: 16933 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6471. Min Act: -0.0000

Data Index: 664234 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1541327 (Python Code)

Max Activating Token Index: 385

Text #18

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6873. Min Act: -0.0000

Data Index: 73197 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1043830 (C4 (Web Text))

Max Activating Token Index: 794