Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2540 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9804. Min Act: -0.0001

Data Index: 261553 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9309. Min Act: -0.0001

Data Index: 1076667 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7598. Min Act: -0.0001

Data Index: 754824 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7741. Min Act: -0.0001

Data Index: 698860 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7743. Min Act: -0.0001

Data Index: 81547 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8239. Min Act: -0.0001

Data Index: 969070 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7562. Min Act: -0.0001

Data Index: 376017 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8017. Min Act: -0.0001

Data Index: 1277913 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7354. Min Act: -0.0001

Data Index: 1186497 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7373. Min Act: -0.0001

Data Index: 546422 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7124. Min Act: -0.0001

Data Index: 812076 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.6418. Min Act: -0.0001

Data Index: 1014906 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.6801. Min Act: -0.0001

Data Index: 173443 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7196. Min Act: -0.0001

Data Index: 628759 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.6748. Min Act: -0.0001

Data Index: 463370 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.6464. Min Act: -0.0001

Data Index: 223773 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.6867. Min Act: -0.0001

Data Index: 399394 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.6817. Min Act: -0.0001

Data Index: 375473 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.7027. Min Act: -0.0001

Data Index: 617454 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.6567. Min Act: -0.0001

Data Index: 973860 (C4 (Web Text))

Max Activating Token Index: 220