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

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

Neuron 3510 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0002

Data Index: 226152 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0560. Min Act: -0.0002

Data Index: 303690 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1181160 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1042866 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1077155 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0473. Min Act: -0.0002

Data Index: 75910 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0469. Min Act: -0.0002

Data Index: 876631 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0464. Min Act: -0.0002

Data Index: 751313 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0464. Min Act: -0.0002

Data Index: 255998 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0461. Min Act: -0.0002

Data Index: 69396 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0446. Min Act: -0.0002

Data Index: 294067 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1569693 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0440. Min Act: -0.0002

Data Index: 585468 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1100151 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0432. Min Act: -0.0002

Data Index: 169575 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1245151 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0423. Min Act: -0.0002

Data Index: 799044 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0423. Min Act: -0.0002

Data Index: 941126 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0423. Min Act: -0.0002

Data Index: 353839 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0421. Min Act: -0.0002

Data Index: 308972 (C4 (Web Text))

Max Activating Token Index: 97