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

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

Neuron 127 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0533. Min Act: -0.0004

Data Index: 1261678 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0004

Data Index: 132202 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0462. Min Act: -0.0004

Data Index: 276432 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0445. Min Act: -0.0004

Data Index: 325664 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0458. Min Act: -0.0004

Data Index: 57367 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0416. Min Act: -0.0004

Data Index: 215082 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0434. Min Act: -0.0004

Data Index: 649972 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0427. Min Act: -0.0004

Data Index: 748482 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0405. Min Act: -0.0004

Data Index: 63121 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0403. Min Act: -0.0004

Data Index: 93375 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0402. Min Act: -0.0004

Data Index: 105545 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0402. Min Act: -0.0004

Data Index: 323810 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0418. Min Act: -0.0004

Data Index: 385284 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0411. Min Act: -0.0004

Data Index: 1143985 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0396. Min Act: -0.0004

Data Index: 531305 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0413. Min Act: -0.0004

Data Index: 700311 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0389. Min Act: -0.0004

Data Index: 582037 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0388. Min Act: -0.0004

Data Index: 1175142 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0388. Min Act: -0.0004

Data Index: 124783 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0405. Min Act: -0.0004

Data Index: 505304 (C4 (Web Text))

Max Activating Token Index: 984