Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 221 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0003

Data Index: 180507 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1476089 (Python Code)

Max Activating Token Index: 182

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1512165 (Python Code)

Max Activating Token Index: 567

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1239236 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0473. Min Act: -0.0003

Data Index: 743290 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1628889 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1079303 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0471. Min Act: -0.0003

Data Index: 512469 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0475. Min Act: -0.0003

Data Index: 259265 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1431519 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0469. Min Act: -0.0003

Data Index: 31732 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0466. Min Act: -0.0004

Data Index: 1369677 (Python Code)

Max Activating Token Index: 748

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1530474 (Python Code)

Max Activating Token Index: 505

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0463. Min Act: -0.0003

Data Index: 681044 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0464. Min Act: -0.0003

Data Index: 759699 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0435. Min Act: -0.0003

Data Index: 52617 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1435885 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0453. Min Act: -0.0003

Data Index: 411054 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1650040 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0455. Min Act: -0.0003

Data Index: 412314 (C4 (Web Text))

Max Activating Token Index: 826