Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2045 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0873. Min Act: -0.0003

Data Index: 862402 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0854. Min Act: -0.0003

Data Index: 280750 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0807. Min Act: -0.0004

Data Index: 112792 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0862. Min Act: -0.0003

Data Index: 209021 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0783. Min Act: -0.0003

Data Index: 873769 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0766. Min Act: -0.0003

Data Index: 809979 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0785. Min Act: -0.0003

Data Index: 687667 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0749. Min Act: -0.0003

Data Index: 825526 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0747. Min Act: -0.0003

Data Index: 701268 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1152944 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0754. Min Act: -0.0004

Data Index: 518959 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0753. Min Act: -0.0003

Data Index: 351770 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1301804 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0807. Min Act: -0.0003

Data Index: 1304186 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0775. Min Act: -0.0003

Data Index: 548496 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0748. Min Act: -0.0003

Data Index: 1295904 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0709. Min Act: -0.0003

Data Index: 932370 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0730. Min Act: -0.0003

Data Index: 242068 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0744. Min Act: -0.0003

Data Index: 623502 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0716. Min Act: -0.0003

Data Index: 644112 (C4 (Web Text))

Max Activating Token Index: 486