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

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

Neuron 1840 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1485 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1293423 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1274683 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1008832 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1138121 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0883. Min Act: -0.0001

Data Index: 610765 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0865. Min Act: -0.0001

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0842. Min Act: -0.0001

Data Index: 314894 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0870. Min Act: -0.0001

Data Index: 996230 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0814. Min Act: -0.0001

Data Index: 676632 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0790. Min Act: -0.0001

Data Index: 245882 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0794. Min Act: -0.0001

Data Index: 611279 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0763. Min Act: -0.0001

Data Index: 93952 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0796. Min Act: -0.0001

Data Index: 320856 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0694. Min Act: -0.0001

Data Index: 769607 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0774. Min Act: -0.0001

Data Index: 438908 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0774. Min Act: -0.0001

Data Index: 984543 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0793. Min Act: -0.0001

Data Index: 879634 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0767. Min Act: -0.0001

Data Index: 510851 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1058924 (C4 (Web Text))

Max Activating Token Index: 945