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

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

Neuron 3280 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1200416 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6730. Min Act: -0.0000

Data Index: 259177 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6350. Min Act: 0.0000

Data Index: 1024548 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6682. Min Act: -0.0000

Data Index: 331636 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6448. Min Act: -0.0000

Data Index: 854000 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6195. Min Act: -0.0000

Data Index: 228792 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6353. Min Act: -0.0000

Data Index: 290675 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6180. Min Act: -0.0000

Data Index: 525318 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5677. Min Act: -0.0000

Data Index: 275867 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5969. Min Act: 0.0000

Data Index: 605008 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5773. Min Act: -0.0000

Data Index: 207198 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6079. Min Act: -0.0000

Data Index: 230793 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1154359 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5804. Min Act: -0.0000

Data Index: 988730 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5680. Min Act: -0.0000

Data Index: 515942 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5673. Min Act: -0.0000

Data Index: 774371 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5686. Min Act: -0.0000

Data Index: 802117 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1093951 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1131708 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5372. Min Act: -0.0000

Data Index: 843149 (C4 (Web Text))

Max Activating Token Index: 808